Reinforcement learning (RL) post-training substantially improves the visual quality, text rendering, and compositional accuracy of diffusion transformers. Because capabilities such as rendering requested text or composing multiple objects are inherently prompt-dependent, a natural hypothesis is that improving them requires learning complex, input-dependent transformations. To isolate how much of these gains an input-independent shift explains, we probe each RL-tuned model with a deliberately simple parameterization: a fixed set of steering vectors added to the block outputs of the frozen base model. On SD3.5-M, these vectors hold 65x fewer parameters than the RL-tuned LoRA (0.29M against 18.8M). We fit them to match the velocity predictions of public RL-tuned checkpoints, with no reward in the objective. Although the vectors are identical for every prompt, token, and sampling seed, they recover 90.0-96.3% of the reward gains of six RL-tuned image models, and 89.8% and 111.9% on two RL-tuned video models. Initialized at zero and trained with online RL, the vectors alone exceed the reward gains of weight-based RL on text rendering (OCR) and human preference (PickScore) on SD3.5-M. A constant shift thus suffices for most of the gain of policy-gradient RL post-training: without new input-dependent transformations, it steers the pretrained generator toward what it can already compute.
We characterise path-independent auto-deleveraging (ADL) rules as an extended log-exponential family. Immunity to account splitting, merging and reopening further restrict the class. Homogeneity (essentially) restricts the class to a one-parameter family ordered by both fairness and platform risk. Its split-proof members continuously interpolate between proportional division and water-filling. Among these rules, decreasing the parameter reduces risk at the cost of increasing inequality in how accounts are treated. This suggests selecting the parameter through an ex-ante calibration to a risk bound on historical data to choose a maximally fair rule subject to that bound. A counterfactual replay of Hyperliquid's ADL episode on 10 October 2025 finds that a range of intermediate parameters significantly improves on the observed allocation in both burden dispersion and subsequent risk statistics.
Reinforcement Learning (RL) has enabled Large Language Models (LLMs) to acquire increasingly complex reasoning and agentic behaviors. In this work, we propose two simple techniques to improve policy gradient algorithms for LLMs. First, we replace the fixed anchor policy during RL with an Exponential Moving Average (EMA), similar to a target network in deep Q-learning. Second, we introduce Top-$k$ KL estimator, which allows for flexible interpolation between exact KL and sampled KL. We derive the stability conditions for using EMA anchor; moreover, we show that our Top-$k$ KL estimator yields both unbiased KL values and unbiased gradients at any $k$, while bringing the benefits of exact KL. When combined with GRPO, the two techniques (EMA-PG) lead to a significant performance boost. On math reasoning, it allows R1-distilled Qwen-1.5B to reach 53.9% on OlympiadBench compared to 50.8% by GRPO. On agentic RL domains, with Qwen-3B base, EMA-PG improves GRPO by an average of 35.6% across 7 datasets of Q&A with search engines, including 29.7% $\rightarrow$ 45.8% on HotpotQA, 27.4% $\rightarrow$ 40.5% on 2WikiMultiHopQA. Overall, we show that EMA-PG is a simple, principled, and powerful approach to scaling RL for LLMs. Code: https://github.com/LunjunZhang/ema-pg
Hybrid architectures have become mainstream among open-weight language models. Their global-attention and bounded-state layers maintain heterogeneous caches whose demands vary with context length and concurrency. We present TideCache, a serving system on CPU--GPU superchips with three components for allocating GPU memory among caches and managing their residency across GPU and host memory. The Transparent Cache Pool redistributes physical pages among cache components behind fixed virtual addresses, preserving cache layouts and backend interfaces. The Cache Streamer uses computation intervals provided by bounded-state layers to prefetch the next global-attention layer's prefix into GPU slots shared across global-attention layers, reducing GPU residency while overlapping layer-wise transfers with computation. Generated KV remains resident. The Request Scheduler selects resident or streamed execution and triggers capacity adjustments according to request size and queue state. Together, they let HBM released by streaming accommodate other cache components and additional requests. Implemented in SGLang and evaluated on GB300 and GH200 across seven model/platform configurations, TideCache completes up to 2.04x as many agent turns, reduces overall P50 per-token latency by 20--59%, and improves agent P50 TTFT by 1.40--3.05x compared with SGLang with HiCache.
High-resolution generation enables video world models to render fine-grained scene structures and textures, but directly generating high-resolution video incurs substantial computational and memory costs. We present ScaleWorld, a causal video model that unifies low-resolution world prediction and high-resolution refinement within a single shared backbone. By refining its own predictions, ScaleWorld produces high-resolution world videos without requiring a separate refinement model. For each video chunk, the shared backbone first completes a low-resolution prediction and then performs one-step high-resolution refinement conditioned on that prediction. To support efficient streaming generation, we maintain separate causal states with a long low-resolution history for prediction and a short high-resolution history for refinement. To address task interference during distillation, we separate specialist optimization from capability consolidation and introduce task-asymmetric on-policy distillation (TA-OPD). This procedure transfers prediction and refinement behaviors from specialized teachers into a shared student through local velocity matching under their respective sampling and history policies. {Extensive experiments demonstrate that ScaleWorld achieves high-quality world generation with improved computational and memory efficiency.
Frontier multimodal language agents such as GPT-6 Astra have demonstrated strong capabilities in controlling robots directly via low-level numerical actions without high-level primitives. However, existing benchmarks report only episode-level success rates, which show neither how these agents succeed nor where they fail. In this paper, we present a systematic action-level analysis of frontier agents on direct robot control across 12 manipulation benchmarks. We introduce AgentRoboCritic, an intent-grounded critique framework in which the policy agent states a local intent alongside each action, and a critic evaluates the action's outcome and failure mode against this intent. Our action-level analysis demonstrates the promising capabilities of frontier agents on direct robot control, including closed-loop recovery from local execution failures, reliable semantic grounding across diverse scenes, and strong zero-shot manipulation without task-specific adaptation. It also identifies their current limitations, including task-relevant physical execution bottlenecks such as grasping and alignment, and uneven recovery across failure modes. Finally, we validate our critic on a 400-action human-annotated benchmark and release a dataset of 12,844 annotated actions alongside a fine-tuned open-source critic, Muse-Glimmer-30B, whose failure-mode accuracy rises from 32.58% to 74.24%, enabling low-cost action-level analysis.
Algorithms frequently assist, rather than replace, human decision-makers. However, the design and analysis of algorithms often focus on predicting outcomes and do not explicitly model their effect on human decisions. This discrepancy between the design and role of algorithmic assistants becomes particularly concerning in light of empirical evidence that suggests that algorithmic assistants again and again fail to improve human decisions. In this article, we formalize the design of recommendation algorithms that assist human decision-makers without making restrictive ex-ante assumptions about how recommendations affect decisions. We formulate an algorithmic-design problem that leverages the potential-outcomes framework from causal inference to model the effect of recommendations on a human decision-maker's binary treatment choice. Within this model, we make a connection between algorithmic recommendations and instrumental variables. Leveraging this connection, we introduce a monotonicity assumption that leads to an intuitive classification of human responses to the algorithm. Under this assumption, we can express the human's response to algorithmic recommendations in terms of their compliance with the algorithm and the active decision they would take if the algorithm sends no recommendation. We showcase the utility of our framework using an online experiment that simulates a hiring task. We argue that our approach can make sense of the relative performance of different recommendation algorithms in the experiment and can help design solutions that realize human-AI complementarity. Finally, we leverage our approach to derive maximin-optimal recommendation algorithms that can be implemented with machine learning using limited training data.
Dataspaces are an emerging concept to enable secure and controlled data sharing between multiple stakeholders. However, most existing dataspace architectures, such as those based on the concepts of IDSA (International Data Spaces Association) and Gaia-X, are heavily concept-driven and require significant effort to implement, making it difficult to quickly build a functional dataspace. Solid (Social Linked Data) offers a compelling alternative by providing a lighter and more practical approach. However, for Solid to function as a true dataspace, like traditional dataspaces, it must be built in a decentralized manner, i.e., the dataspace must consist of more than a single Solid server. However, this decentralization introduces a key challenge: Data Discovery. Unlike traditional dataspace architectures, which often include predefined components such as data catalogs to facilitate data discovery and access, Solid does not inherently provide such mechanisms. As a result, managing and locating relevant data across multiple Solid servers and pods becomes a significant barrier to usability. To address this gap, we present a FAIR-compliant data catalog for Solid. Our catalog follows the FAIR principles (Findability, Accessibility, Interoperability, and Reusability) by integrating semantic models that describe all available data sources within the Solid ecosystem. This approach enables enhanced data discovery, improves accessibility through standardized metadata, enhances interoperability between different data sources, and promotes data reuse across applications. By bridging this critical gap, our catalog improves the usability of Solid-based dataspaces, making them a viable option for decentralized and open data ecosystems, such as smart city applications.
Graph-based data structures such as DiskANN, HNSW, and NSG constitute the state of the art for large-scale approximate nearest-neighbor (ANN) search. Indyk and Xu introduced the notion of $α$-reachable graphs, which include graphs built by DiskANN's slow-preprocessing construction, and proved that greedy search achieves an approximation factor of $\tfrac{α+1}{α-1}$. Independently, Al-Jazzazi et al. proposed adaptive beam search (ABS) with a relaxation parameter $γ> 0$, showing a $\tfrac{2}γ$ approximation on navigable graphs ($α\approx 1$), where greedy search admits no guarantees. In this work, we unify and generalize these results by proving that ABS with parameter $γ$ on $α$-reachable graphs achieves an approximation of $\tfrac{α+1}{α(γ+1)-1}$ for any metric. Moreover, on sorted $α$-reachable graphs (introduced by Gollapudi et al.) under the $\ell_2$ metric, we obtain the tighter bound $\max\bigl(\tfracα{α(γ+1)-1}, \tfrac{α^{2}+1}{α^{2}(γ+1)-1}\bigr)$. Beyond these theoretical results, we design a beam predictor using features inspired by fine-grained analysis of ABS, trained via a constrained objective that minimizes mean distance computations subject to a target recall. On three 100-million-point benchmarks, using graphs built by DiskANN's practical construction, beam predictor lowers mean query latency on SSD-resident indices at matched recall by up to $29.6\%$ relative to classical beam search (CBS). Relative to ABS, it is faster in $11$ of $15$ settings, by up to $6.5\%$, and at most $1.4\%$ slower in the other $4$; at $95\%$ recall, its advantage over ABS grows from $0.8$--$4.2\%$ for $100$ neighbors to $4.6$--$5.6\%$ for $500$ neighbors. In memory, it needs $1.3$--$23.7\%$ fewer distance computations than CBS and $0.0$--$3.9\%$ fewer than ABS.
Collecting and labeling inertial measurement unit (IMU) data for human activity recognition (HAR) is expensive, and models trained on one group of subjects often fail to generalize to unseen individuals. Even with balanced data, classifiers struggle to distinguish dynamically similar activity classes and benefit from targeted augmentation. We explore whether synthetic IMU data generated in the representation space of a pretrained biosignal encoder, Bio-PM \cite{b1}, can serve as a practical augmentation source. Rather than synthesizing raw signals, we leverage Bio-PM's frozen encoder to convert 10-second IMU windows into token embedding sequences and train class-conditional decoders in this space: (1) an autoregressive transformer decoder that predicts tokens sequentially, and (2) a diffusion decoder that learns the token distribution through a denoising objective. We analyze generation realism through distributional metrics and embedding-space visualizations, evaluate downstream utility through leave-one-subject-out HAR classification, and present a PatchDecoder for approximate raw waveform reconstruction. Our diffusion decoder achieves a Train-on-Synthetic-Test-on-Real (TSTR) macro-F1 of 0.68, demonstrating that generated tokens are realistic enough to train a classifier that transfers to real data. Combining synthetic-token augmentation with a 320-dimensional gravity-aware feature representation raises LOSO macro-F1 from 0.729 to 0.809 over a real-only baseline across 51 subjects on the WISDM benchmark, with statistically significant gains concentrated in the most challenging activity classes. These results demonstrate that high-fidelity generation in a pretrained encoder's representation space is achievable and practically useful for cross-subject HAR augmentation.
Depth Pro 2: Sharp and Temporally Consistent Metric Monocular Depth
Peiyun Hu, Marko Mihajlovic, Lyndon Duong, Lahav Lipson, Wei Dong, Amaël Delaunoy, Stephan R. Richter, Vladlen Koltun
AI 速读 基于摘要
Depth Pro 2 用一个可扩展的单一网络同时处理图像与视频,在原生分辨率下预测兼具度量准确、边界锐利与时序一致的稠密深度。
cs.CV · cs.LG
查看原文摘要
We present Depth Pro 2, an approach to estimating dense metric depth for images and video at full resolution. By analyzing prior methods for monocular depth estimation, we find that they commonly trade off temporal consistency and boundary sharpness: multi-frame methods favor consistency, single-frame methods favor sharpness. To overcome this trade-off, we train a single, scalable network that processes both images and video and predicts depth maps at native resolution. Depth Pro 2 produces depth maps that are metrically accurate, sharp, and temporally consistent all at once, outperforming prior work in all of these dimensions. We release a family of models that define a new Pareto frontier in terms of metric accuracy, sharpness, temporal consistency, and runtime. We release code and weights at https://apple-aiml-research.github.io/ml-depth-pro-2/
LLM-based agents are becoming increasingly capable at discovering, validating and patching vulnerabilities in real software, and vendors and researchers report that this is already changing how vulnerabilities are found and fixed. These claims, however, are scattered across papers, vendor reports and disclosures and are rarely comparable. We introduce a framework that rates these capabilities on an autonomy scale modeled on the levels of driving automation, and qualifies each claim by its correctness, its availability and the strength of its evidence. We use this framework to systematize the published evidence on LLM capability in vulnerability research. We find that agents discovered, validated, and patched vulnerabilities in real-world software without human intervention before the restricted frontier models of 2026, and that open-weight models subsequently attained comparable autonomy for discovery and validation. We then measure the consequences of evolving LLM security capabilities in a decade of public vulnerability records, advisories and exploitation data. In 2026 the number of disclosed vulnerabilities more than doubled, with an increasing share rated critical or high, and severe bugs that had survived a decade or more in widely used code were reported several times more often than before. Yet the time between the stages of a vulnerability's life, from report to fix and from disclosure to attack, has not shifted noticeably so far. We grade the mitigations proposed in the literature with an explicit rubric and draw guidance for each group of stakeholders from the best-supported ones.
Simulating rigid-body dynamics with contact is fundamental to robotics, from motion synthesis and control to mechanism design. Many widely used simulators rely on cone complementarity formulations, whose physical assumptions and numerical solution require substantial background. While excellent surveys, monographs, and course notes exist, they mostly address computational mechanics or computer graphics or document a single simulator. To the best of our knowledge, a self-contained pedagogical treatment for robotics, bringing these formulations and their solvers together with complete derivations and a unified notation, does not yet exist. This tutorial addresses this gap by connecting rigid-body dynamics, conic optimization, and frictional contact. In particular, we explain how complementarity conditions encode non-penetration and frictional dissipation, determining separation, sticking, and sliding without prescribed contact modes. We distinguish equivalent transcriptions from convex relaxations, showing how the latter can introduce artifacts such as lift-off and creep. We examine the existence and uniqueness of motion and contact forces, including the solver's role in selecting among multiple solutions. We then compare first-order and Newton-based methods, explain regularization and proximal strategies, and discuss trade-offs between computational cost, robustness, and physical fidelity. Connections to widely used simulators, optimal control, and differentiable simulation help readers interpret simulation results, choose suitable formulations and solvers, and develop their own contact dynamics routines.
Acquiring every feature of an instance is often costly: a measurement can carry a monetary price, a time delay, or a privacy cost. Active Feature Acquisition (AFA) addresses this by learning a policy that decides, per instance, which features to acquire under a budget. Existing AFA methods train this policy by optimizing a self-constructed utility target rather than distilling an explicit teacher. We construct this teacher explicitly. At training time the label and the unobserved feature values are available, and together they determine the teacher in closed form: an oracle that ranks every candidate by its effect on the downstream predictor's error. OracleImitator distills this ranking into a deployable policy by soft-target imitation. Across multimodal medical diagnosis and the AFABench benchmark, OracleImitator matches or outperforms existing AFA methods across the budget range, recovering 90% of the attainable accuracy gain at under a quarter of the acquisition cost. Because the teacher is an explicit algorithmic object rather than an implicit optimization target, we can also measure directly how much of its ranking is recoverable by a policy restricted to what is visible at deployment.
In-context learning (ICL) enables language models to perform new tasks from demonstrations without weight updates. However, every ICL inference requires processing the full set of examples, resulting in inefficient deployments, and how ICL works mechanistically is not fully understood. Prior work compresses ICL into fixed activation vectors extracted from specific layers or positions, but these input-independent interventions fail on complex tasks where the output depends on fine-grained interactions with the input. By analyzing the ICL forward pass, we show that each attention head's output is an affine transformation of its context-masked counterpart, and that the parameters of this transformation are empirically stable across samples for a given task. Building on this, we introduce Task Operator (TO), which replays this transformation as an analytically derived update to the attention output projection. Across lexical, algorithmic, and reasoning tasks, TO achieves the best overall performance among prior methods and substantially narrows the gap between zero-shot inference and ICL. We further show that the extracted knowledge concentrates in a task-specific sparse circuit across layers and positions, and that averaging operators from disjoint demonstration batches enables effective many-shot scaling without expanding the context window. Our code is available at https://github.com/gzxiong/task_operator.
Robotic vision-language-action (VLA) models can execute diverse individual manipulation skills, yet they still struggle with long-horizon loco-manipulation tasks, where temporal structure, skills, and precision are tightly coupled within a monolithic model. We propose Physically Grounded Execution (PGX), a framework that offloads temporal and precision control to two classical training-free components, allowing the VLA to focus on stage-specific skill dynamics. PGX decomposes long-horizon loco-manipulation into three layers: (i) a predicate-based state machine governs task progression, using physical predicates to gate phase transitions, trigger recovery, and coordinate navigation and waiting. Shared predicate semantics connect offline demonstration segmentation, online execution, and stage-wise evaluation; (ii) VLA skills operate within active manipulation phases, with flat or stage-trained models concentrating on task-relevant actions; and (iii) world-coordinate locking (WCL) maintains spatial consistency through base station keeping, object-relative positioning, and world-anchored contact targets. We demonstrate the effectiveness of PGX with extensive experiments conducted on three simulated tasks and one real-world task using a Unitree G1 humanoid robot for long-horizon loco-manipulation, showing improvements in stage progression and task success rates. Project page is available at: https://kl-research.github.io/pgx
Code2Video uses agent-authored 3D proxies to guide video generation, enabling explicit control over structure and dynamics. However, how to construct proxies and prompts for optimal downstream quality remains underexplored, as do the capabilities and limitations of this paradigm. Through controlled experiments and blinded human evaluation, we study proxy granularity, physics simulation, and prompting. The results reveal task-dependent trade-offs: coarse proxies favor natural motion, while medium-grained proxies favor consistency. Physics simulation and proxy-aligned prompting further improve average quality. Guided by these findings, we introduce Coda-DaVinci, a task-adaptive agentic framework for Code2Video generation that selects between proxy-guided and direct generation, adapts modeling granularity to each entity, and coordinates simulation with proxy-grounded prompting. Its multi-agent harness preserves scene assets and guides repairs through visual inspection and independent review. Experiments demonstrate leading instruction following on VTR and scene consistency on R2M, improved physical plausibility over direct generation, and higher visual realism than the compared Code2Video baselines. Long-video evaluations further show gains in event structure and consistency across successive interactions, while revealing limitations in transition stability and adherence to scene settings.
Large Vision Language Models (LVLMs) show promise in medical applications, but their inability to faithfully ground responses in visual evidence raises serious concerns about clinical trustworthiness. While visual attribution methods are widely used to explain LVLM predictions, whether these explanations actually reflect the visual evidence underlying the model's decision is largely unverified, since ground-truth annotations for internal model reasoning are typically unavailable. We address this question for chest X-ray (CXR) reasoning by developing a causal evaluation framework that retains only CXR-VQA samples for which the expert-annotated region is verified, via counterfactual editing, to be causally responsible for the model's prediction. Using this framework across 11 attribution methods, six open-source LVLMs, and two output modes (direct answer and step-by-step reasoning), we find that existing attribution methods often fail to identify the evidence used by LVLMs. To address this failure, we propose MedFocus, a concept-based attribution method that localizes clinically meaningful anatomical regions via unbalanced optimal transport and measures their causal effect on model outputs through targeted interventions. MedFocus produces spatial, concept-level, and token-level attributions and substantially outperforms prior methods, taking a step toward more trustworthy attribution for medical LVLMs. Our data and code are available at https://github.com/gzxiong/medfocus/.
Vision-language-action (VLA) models adapt web-pretrained vision-language models to output robot actions, so that web knowledge carries over to physical control. In under four years the field has grown from RT-2, the first VLA, to open models that fine-tune on a single consumer GPU and proprietary generalists that clean unseen homes. VLA research joins robotics, computer vision and language modelling, so this survey is written for researchers and practitioners from each of these fields. It reviews 89 works from December 2022 to October 2026, mainly on manipulation and navigation, plus humanoid control, world-action models and evaluation. Seven design axes follow a VLA's life cycle: model design (inputs and memory, architecture, action output, intermediate predictions), training (pretraining data, post-training) and deployment (real-time execution). We compare 22 models on these axes, with their training data, model size, inference speed and hardware. Three trends emerge. (i) Training data has broadened beyond teleoperated robot data (about 10,000 hours for $π_0$) to community-collected episodes and egocentric human video (20,000 hours for GR00T N1.7). (ii) Model sizes have split into two groups: most recent models have 3-7 billion parameters; a new group under one billion runs on consumer GPUs. (iii) Generalist VLAs handling both manipulation and navigation are emerging, such as UniVLA and Qwen-VLA. We also compare VLAs with world-action models, which predict future observations as well as actions, and review evidence that some VLAs with near-perfect benchmark scores fail after small scene changes. A practitioner's guide gives a default for each design decision, and a glossary supports readers new to the field.
Activation steering controls LLM behaviour towards target behaviour by intervening in internal representations, yet it often degrades reasoning and retrieval performance. We argue that a primary cause of this trade-off is attention rerouting: steering vectors alter query-key matching, shifting attention away from contextually important tokens toward less informative ones. To address this, we propose Steering via Key-Orthogonal Projections (SKOP), a steering method that constrains harmful attention rerouting without eliminating steering efficacy. SKOP achieves this by preserving attention patterns on a small set of focus tokens the model relies on for reasoning and retrieval, while allowing redistribution among less critical tail tokens. Across multiple steering benchmarks, we show that SKOP achieves the best joint steering-utility trade-off, reducing utility degradation by 5-7x while retaining over 95% of vanilla steering efficacy. Our results further suggest that, in long-context retrieval settings where vanilla steering approaches are ineffective, SKOP can maintain robust performance by avoiding attention rerouting.
Does post-training change what a language model represents, or how this representation is read out into an answer? We compared linear probes with the models' own answers, analyzed with signal detection theory, in six open-weight base models and their post-trained versions. For judgments of whether German texts were written by a human or an AI, probes and word n-gram classifiers separated the classes well, but the answers did not and often ordered the texts inversely. Post-training lowered the sensitivity of the answers on average ($Δd' = -0.34$ across model families; -0.29 across three prompts). It also changed the use of a stated base rate: Base models shifted their log-odds by less than the stated change in prior odds, most post-trained models by more. In two models with stage-wise checkpoints, the change occurred during supervised fine-tuning, model stitching implicated the early layers, and from mid-depth on internal states at positions after the text, not those of the text, transferred the change between checkpoints. Our corpora cannot be shared, so we add a case reproducible from public data, the truth of negated statements. Here, post-training acted in the opposite direction: Probes decoded truth at or near ceiling in every model, the answers of several base models did not use it, and post-training repaired them; by mid-depth the repair resided at the positions after the statement; below it, the representation of the statement contributed, strongly in one of four models. In a training study, adding 2,000 correctly labeled authorship judgments of news texts to otherwise identical fine-tuning data improved the answers on our newspaper and textbook corpora and inverted them on the chats, where they followed a news-trained probe of the base model. Post-training thus changed how a judgment is read out of what a model represents, and a small training signal can set its direction.
Quantum algorithms for differential equations have the potential for substantial algorithmic speedups over classical methods. However, they rely on certain assumptions and abstract oracle specifications that leave their practical feasibility and computational advantages for realistic applications unclear. Here we formalize the concept of an end-to-end quantum algorithm for differential equations as one that accepts classical inputs and returns classical outputs, and provide implementations for algorithmic primitives in constructing such algorithms. We present a tailored end-to-end quantum algorithm for the linearized Poisson-Boltzmann (LPB) equation, a partial differential equation (PDE) with variable coefficients widely used in simulating a biomolecular system. We explicitly implement all aspects of the algorithm, from preparing an initial state to generating a quantum solution and estimating properties of the system. In particular, we develop a new discrete representation for variable-coefficient PDEs on a grid that enables efficient implementation of the operator oracle, and build on a recent technique based on optimal wavelet preconditioning to generate a quantum solution with a cost independent of the condition number of the discretized operator. We show the algorithm can be implemented by quantum circuits of size polylogarithmic in both the number of grid points $N_g$ and the inverse of the desired accuracy $\varepsilon$, with an overall gate cost polylogarithmic in $N_g$ and quasilinear in $1/\varepsilon$. We also show the classical preprocessing to construct the circuits has polylogarithmic cost in $N_g$ and $1/\varepsilon$. Our work provides a concrete end-to-end quantum algorithm for a PDE of practical value, demonstrates an exponential improvement in scaling with $N_g$ over classical methods, and provides a foundation for assessing its potential quantum advantage in practice.
Remark: This work is in submission at STOC'27 and thus the full manuscript has been publicly posted on the conference website since November 3rd, 2026. Inspired by the Codeword-Hash Structure problem recently introduced by Cakan (arXiV, 2026) to separate $\mathsf{QMA}$ from $\mathsf{QCIP}$, we introduce a new problem called Codeword-Hash pairs in Noise ($\mathsf{CHN}$) and prove that, in the query complexity model, it is in $\mathsf{QMA}$ but hard for the $\mathsf{QCMA}$ hierarchy $\mathsf{QCMAH} = \bigcup_{d\geq1}\mathsf{QCMA}^{\mathsf{QCMA}^{\cdots^{\mathsf{QCMA}}}}$, the classical-witness quantum-verifier analogue of $\mathsf{PH}=\bigcup_{d\ge1}\mathsf{NP}^{\mathsf{NP}^{\cdots^{\mathsf{NP}}}}$. Using this problem, we show that there exists a classical oracle ${O}$ such that $\mathsf{P}^{O}=\mathsf{BQP}^{O}=\mathsf{QCMA}^{O} =\mathsf{QCMAH}^{O} \subset \mathsf{QMA}^{O} \text{ but } \mathsf{QMA}^{O}\not\subseteq\mathsf{QCMAH}^{O},$ thus showing that quantum state or quantum proof advantage could exist even if classical computers can efficiently solve any problem that can be quantumly verified with a classical proof. Further, using our problem, we show that various quantum cryptographic primitives can exist even when $\mathsf{P} = \mathsf{QCMA}$ and thus neither quantum-computable one-way functions nor (verifiable) quantum computational advantage exist. In particular, relative to a classical oracle ${O}$ with $\mathsf{P}^{O}=\mathsf{BQP}^{O}=\mathsf{QCMA}^{O}=\mathsf{QCMAH}^{O}$, there exist pseudorandom states with classical keys and public-key encryption with copy-protected quantum decryption keys and classical public keys and ciphertexts, among other primitives, answering an open question of Kretschmer, Qian, and Tal (STOC 2025).
Cardiometabolic diseases are leading causes of ill health, and neighbourhoods that support everyday walking may help reduce them. Studies often report lower disease prevalence in more walkable neighbourhoods. However, because walkability operates across multiple spatial scales, city-wide associations may conflate local neighbourhood form with broader metropolitan structure and co-varying environmental exposures. Here we show that while much of the walkability--morbidity association in Greater London operates through the city's macro-scale spatial structure, local alignment persists beyond it. Using an open five-component walkability index for 4,994 London census units and recorded prevalence of eight cardiometabolic conditions from primary-care registers, we found that higher walkability was inversely associated with all eight outcomes after adjusting for demographic composition and deprivation; one standard deviation higher walkability corresponded to 1.43 percentage points lower hypertension prevalence. Walkability followed a centre--periphery gradient, with a radial model explaining 74.2\% of its variation. Coefficients were reduced by 2--43\% within boroughs and 11--75\% after centre--periphery adjustment. After spatial-error adjustment, no clear association remained for obesity; coefficients for the other seven were reduced by 83--99\% relative to comparable log-scale models. Nevertheless, observed associations were more extreme than those from surrogate walkability surfaces preserving this spatial structure, for all eight outcomes in the primary analyses and for five after adjustment for nitrogen oxides. These findings caution against interpreting city-wide walkability coefficients as neighbourhood effects independent of wider metropolitan structure, and highlight the need for studies of neighbourhood form and health to disentangle global and local spatial structure explicitly.
Large language models (LLMs) are often used to perform a form of conditional inference. In-context learning is one implicit way to do this. The prompt specifies a context and the model's output is treated as an estimate of the corresponding conditional distribution. If this interpretation holds, then LLM estimates should satisfy basic probabilistic identities. In particular, the law of total probability asserts that prior-weighted conditional distributions aggregate into population-level marginals over any valid partition of the population. In this work, we investigate to what extent LLM estimates adhere to this self-consistency principle. We use binary trees as an evaluation scaffold to recursively partition a population into increasingly fine-grained subpopulations. We then prompt LLMs with verbalized subpopulation descriptions in context, aggregate the resulting estimates back into population-level estimates, and compare them across partitions of varying granularity. Translating these comparisons into a benchmark score and evaluating frontier models across problem domains, we demonstrate widespread violations of basic consistency properties. An in-depth study of persona prompting further reveals a pattern we call the macro fallacy: estimates reconstructed from more fine-grained subpopulation responses are often better aligned with human reference data than direct population-level estimates. The effect persists across variations in partitioning, verbalization, and estimation task, suggesting that models possess relevant subpopulation knowledge but do not reliably propagate it into aggregate estimates. This gap establishes statistical self-consistency as an unsaturated, reference-free criterion for evaluating LLMs.
Generating property-optimized mRNA sequences is central to applications such as vaccine design and protein replacement therapy, but remains challenging due to limited data, complex sequence-function relationships, and the narrow space of biologically viable sequences. Generative methods that drift away from the data manifold can yield sequences that fail to fold, translate poorly, or are otherwise nonfunctional. We present RNAGenScape, a property-guided manifold Langevin dynamics framework for mRNA sequence generation that operates on a learned manifold of real data. By performing iterative local optimization constrained to this manifold, RNAGenScape preserves favorable computational viability proxies, accesses reliable guidance, and discourages excursions into regions poorly supported by the training data. The framework integrates three components: (1) an autoencoder jointly trained with a property predictor to learn a property-organized latent manifold, (2) a denoising autoencoder that projects updates back onto the manifold, and (3) a property-guided Langevin dynamics procedure that performs optimization along the manifold. Across three real-world mRNA datasets spanning two orders of magnitude in size, RNAGenScape increases median oracle-predicted property gain by up to 267% and success rate by up to 31%, while maintaining good biological viability proxy measures and achieving competitive inference efficiency compared to existing generative approaches.
Multimodal image generation systems have made rapid progress and increasingly emphasize content safety. However, their safety mechanisms tend to rely on a single modality and lack joint consideration of both visual content and text prompts, particularly in instruction-guided image editing, where the uploaded image may itself carry risk. We thus introduce EditSafetyBench, a benchmark that measures system-level safety awareness of advanced image editing systems, containing 5,940 image-instruction pairs, covering safe and unsafe images across 11 risk categories and three edit intents. We then probe the benchmark dataset on four systems, including Gemini, GPT, Qwen API, and Qwen Local. Based on our evaluation, we observe a systematic text-vision safety mismatch: Gemini and GPT refuse 87.1\% and 81.6\% cases containing unsafe-intent editing prompts, while only refusing 24.2\% and 22.4\% cases with both unsafe images and neutral instructions. At the category level, most risks are considered inconsistently by different systems, e.g., GPT allows 70.4\% editing attempts of unsafe political content while Gemini only allows 34.8\%. Notably, sexual content shows the strongest visual sensitivity, likely benefiting from mature NSFW identification works. Our findings highlight the need for safety guardrails that jointly reason over both visual and textual modalities in image editing systems.
Tree-based machine learning methods are widely adopted for their interpretability and state-of-the-art accuracy on tabular data. These methods face efficiency challenges on conventional architectures due to irregular memory access patterns during tree traversal. Prior work uses analog CAM to accelerate tree traversal, but inefficient mapping requires exponentially more analog CAM columns as tree depth increases. Accuracy is also degraded by device non-idealities such as programming variations and soft decision boundaries. To address these challenges, we propose ACTIVAR, a compact variation-tolerant tree implementation in a dense analog CAM array via software-hardware codesign. On the software side, we introduce an analog-CAM-aware compact tree model that employs hierarchical subtrees with shared features to maximize hardware utilization. This dense mapping introduces redundancy, improving both model accuracy and hardware defect tolerance. Additionally, we develop Variation-Enhanced Training, which utilizes a fuzzy overlap boundary strategy to build models resilient to analog noise. On the hardware side, we design a FeFET-based analog CAM cell with a driver to sharpen decision thresholds and implement a pipelined multi-core architecture to optimize throughput and energy consumption. Across 13 classification and regression datasets, ACTIVAR maintains near-software-level accuracy while reducing hardware overhead by up to 99% compared with prior analog-CAM-based soft-tree designs. Under realistic hardware noise conditions, ACTIVAR limits accuracy degradation to just 3.7% on the MNIST dataset, whereas baseline models suffer a catastrophic 49.6% drop. Furthermore, the ACTIVAR architecture achieves energy efficiency gains ranging from $10^4$ to $10^6$ times over commercial general-purpose processors, establishing it as a highly efficient solution for high-capacity machine learning at the edge.
Vision-Language-Action (VLA) models have advanced rapidly in language-conditioned robotic manipulation, yet existing benchmarks mainly evaluate gripper--object contact and largely ignore how objects interact with the environment through gravity, friction, inertia, and mass distribution. As a result, it remains unclear whether current policies truly understand physics or merely interpolate from their training data. We address this gap through the lens of dynamic extrinsic dexterity and introduce PhyDEX, a throwing benchmark in which a robot must infer an object's mass, center of mass, and friction to send it to a destination beyond its kinematic workspace. PhyDEX contains 35K trajectories (143 hours) across nine tasks and 100 scenes, covering uniform, irregular, and dynamic-mass objects with static, multiple, and moving destinations. All data are generated by a scalable, fully automatic pipeline that combines grasp generation, motion planning, and closed-loop throw optimization under randomized physical properties. We evaluate three representative VLAs, GR00T N1.7, DynamicVLA, and ForceVLA, and find that all achieve success rates below 3\%. Our analysis reveals two key bottlenecks: limited robustness of pretrained models, which causes most failures before the throw, and physical blindness, as providing ground-truth physical properties roughly doubles success. Experiments on a humanoid robot and in the real world show the same failure patterns. We hope PhyDEX will drive the development of physically grounded robot policies.
Generative engines synthesize retrieved web pages into answers, recommendations, and rankings. Generative engine optimization (GEO) services sell visibility in these answers by publishing promotional articles on user-generated-content (UGC) platforms for paying clients. Such promotion raises concerns in medical and financial domains, where misleading advice can cause harm. To study the severity of this problem, we measure one such paid-content operation across three major Chinese UGC platforms, uncovering 1,985 accounts associated with the network comprising 466,357 inferred promotional placements. We find that the network promotes products across diverse categories through a growing pool of accounts, conducting coordinated campaigns spanning months across multiple platforms while evolving its listicle content over time. Across nine generative engines from both the US and China, we find that 4.5% to 20% of retrievable cited pages are attributable to the network, depending on how strictly attribution is drawn. On eight of these engines, its clients are named in 52% of answers, against 68% for category leaders. Our work demonstrates the effectiveness of UGC GEO placement at influencing generative engine outcomes, and reveals content-level defenses as insufficient against coordinated UGC placements, where account-level and platform-level signals are necessary for proper defense.