Ziad Ismaili Alaoui, Oded Lachish, Nikhil S. Mande
AI 速读 基于摘要
作者在割查询模型下证明,确定性寻找锦标赛中“国王”的查询复杂度为 Θ(n)。
cs.CC · math.CO
查看原文摘要
A king in a tournament is a vertex from which every other vertex is reachable by a directed path of length at most two. We study the deterministic query complexity of finding a king when a query specifies a set of vertices and returns the number of edges directed from that set to its complement. We prove that this complexity is $Θ(n)$ for $n$-vertex tournaments. To show this, we first show that every correct deterministic algorithm in this model must output a maximum-outdegree vertex, even though a king need not have maximum outdegree. We then give an adversary whose answers, after too few queries, remain consistent with a tournament in which the algorithm's output does not have maximum outdegree.
Legal Question Answering (QA) over statutory texts is a challenging task in Natural Language Processing (NLP), especially in low-resource settings with complex legal systems. It requires answers that are precise and grounded in the law. However, to the best of current knowledge, no existing extractive QA benchmark provides exact answer spans from statutory texts across all seven Indian Intellectual Property Rights (IPR) Acts. This paper presents IndicIPR-QA1, an extractive QA benchmark for Indian IPR laws. The proposed dataset contains 4,462 QA pairs from 1,116 statutory contexts across seven Acts. Questions and answers are generated using GPT-4o and validated through nine automatic quality checks, single and multi-model LLM evaluations, and a 200-pair human audit. Section-level partitioning prevents source-context overlap across the training, validation, and test sets. Further analysis examines answer span length, lexical overlap, and multi-clause structure across the corpus and individual Acts. BM25 achieves a token-level F1 score of 20.21, while fine-tuned InLegalBERT reaches 85.02 under a unified sliding-window inference protocol. The large performance gap between BM25 (20.21 F1) and InLegalBERT (85.02 F1) shows that simple word matching is not enough to answer these legal questions. Performance also varies across the seven Acts, indicating substantial differences in answer-extraction performance.
Safety alignment for Large Language Models is heavily focused on English with limited multilingual representation, particularly damaging low-resource language performance. Related open training datasets are often limited in size or do not follow region-localized harmful topics to broaden the scope of alignment beyond cultures. We propose a scalable template-based augmentation pipeline to produce massive multilingual refusal and benign corpora, extracting safe templates from harmful prompts, translating them and then filling in the slots with culturally authentic entities, both harmful and benign. As a result, we release MSafeTemp, a validated corpus spanning 60 languages useful for multilingual safety alignment and evaluation. Using the dataset, we show that English-only evaluation misjudges multilingual safety: for several models, attacks that fail in English succeed once translated, while culturally localized variants expose further failures that translation alone misses. We also confirm that augmenting safety training data through templates allows for higher diversity and quality of alignment, resulting in improved safety performance beyond English. MSafeTemp and the respective pipeline are aimed at facilitating research and development of safer and more responsible models for less-represented cultures.
We develop design methodologies for the rate profile of polarization-adjusted convolutional (PAC) codes tailored to successive cancellation list (SCL) decoding. The crux of our approach is two-fold: first is the creation of a modified density evolution Gaussian approximation (DEGA), called conditional DEGA (CDEGA), to analyze the decoding process in the presence of errors; second is the creation of a dangerous-path occupancy metric to find the conditional occupancy of bit-errors in a finite list. Our approach not only illuminates the role of rate-one precoding, but also provides insight into why certain information sets are particularly well suited to PAC codes. We demonstrate the usefulness of CDEGA and dangerous-path metrics with algorithms that create new information sets, as well as precoders that are extremely sparse yet competitive. In particular, we design codes of length $N \leq 512$ with various rates and list sizes, all of which offer at least half a dB gain over traditional PAC codes at an FER of $10^{-3}$ and improve upon state-of-the-art results.
Large language models (LLMs) are increasingly used as computational models of human language processing, yet it remains unclear which components of their representations drive alignment with neural activity. Here, we use ridge reduced-rank regression to identify the brain-predictive subspace of LLM representations: the representational directions that support linear prediction of neural responses. Across three naturalistic language-listening datasets spanning intracranial electrophysiology and fMRI, and six model conditions spanning autoregressive, bidirectional masked, and randomly initialized language models, we find that full linear encoding performance can be recovered using only 1-3% of the original embedding dimensionality. These low-dimensional subspaces generalize across held-out participants and, to a lesser extent, across datasets, suggesting that neural predictivity is concentrated in a compact and partially shared representational space. We next compare these brain-predictive directions with the principal axes of variation in the embeddings. Principal component analysis requires substantially more dimensions to recover neural prediction, demonstrating that the directions most useful for predicting neural activity are distinct from those capturing the most overall variance within LLM representations themselves. Finally, characterizing the learned subspaces allows us to surface interpretable features that are overrepresented in neural activity above and beyond the LLM representations. Together, these results show that LLM-brain alignment is supported by a small, structured subset of model representations and provides a framework for better understanding exactly why these representations align. Code can be found at: https://github.com/thefinnlab/low-rank-alignment
RecHash is a stateful sequential authentication construction based on paired hash-chain openings and an authenticated record history. It develops the decreasing position relation of the 2019 hash-entangled construction, whose exact integer normalization yields a two-coordinate constant-sum antichain. Direct proportional reuse is constrained by integer capacity and multiplicative contraction. The main construction instead assigns each record to a predetermined chain segment, with complementary positions encoding each digest block. All digests fit every scheduled slot, independently of preceding messages. For an $\ell$-bit digest distributed over $k$ equal-length chain pairs, balanced allocation gives $\lfloor L/(2^{\lceil\ell/k\rceil}+1)\rfloor$ slots. A 256-bit digest, 32 pairs, and length 65535 provide 254 application records followed by a renewal certificate, with 2048 bytes of openings per record for 256-bit chain outputs. We give a complete segmented state transition, a worked trace, exact allocation and resource results, and a renewal-free security-composition theorem conditional on authenticated history and an adaptive one-step guarantee. The analysis relates the construction to constant-sum encodings and standardized hash-based signatures; a concrete post-quantum reduction and security across renewal remain open.
Voice-cloning TTS models synthesize an unseen speaker's voice from brief speech prompts, but it remains unclear which acoustic properties they represent and use. We introduce a feature-based interpretability framework for autoregressive voice-cloning TTS models, analyzing features from sparse autoencoders (SAEs), PCA, and random directions via sparse probing, steering, and quantitative auto-interpretability. We focus on Qwen3-TTS and extend probing and steering to $5$ additional models to test generalization across architectures. These models encode concepts like pitch, energy, noise, and accent, but sparse prediction and steering are effective only for some concepts. Strong probing does not always translate to steering or vice-versa. SAEs are useful for sparse probing of human-labelled concepts and novel-concept discovery, while PCA is competitive for dense probing and steering. Auto-interpretability finds $684$ automatically validated SAE features in Qwen3-TTS covering speaker clusters, speaking style, and recording conditions beyond known concepts. Overall, we perform a comprehensive interpretability study of autoregressive voice-cloning TTS models.
To avoid moderation and surveillance on social media, some users routinely invent indirect linguistic expressions (ILE) that camouflage sensitive meanings. Such disguised expressions surface as algospeak, euphemisms, and adversarial obfuscation, depending on intent and context, and often involve recurring encoding mechanisms. We propose a comprehensive, mechanism-oriented taxonomy of ILE that abstracts away from communicative goals and instead categorizes the underlying operations through which meaning is encoded and recovered. We evaluate the taxonomy by incorporating it into large language model (LLM) prompts and comparing it with four existing taxonomies and a no-taxonomy baseline, using 2,000 manually annotated TikTok and Bluesky posts. The proposed taxonomy attains the strongest document- and span-level performance across three LLMs. Compared with the best-performing benchmark, its document-level gains are +3.8 accuracy/+4.3 macro-F1 percentage points for GPT-5.4, +0.9/+1.3 for Sonnet 4.6, and +2.1/+2.2 for DeepSeek V4. While the direction of improvement is consistent, the magnitude is model-dependent. The span-level gains are mainly driven by higher recall, sometimes at the cost of precision. In an additional cross-lingual evaluation of 800 Chinese codedlanguage reviews, the unadapted taxonomy also achieves the highest document- and span-level F1 across the three LLMs. The empirical results reveal the importance of a comprehensive, mechanism-oriented taxonomy as a stable scaffold for detecting emerging coded language and a useful input to content moderation. Disclaimer: This paper contains content that may be profane, vulgar, or offensive.
AI has made remarkable progress in mathematics, solving challenging problems with machine-checkable proofs in Lean, yet typically relying on predefined mathematical definitions and formal specifications. This raises a natural question: can it reason rigorously about an unknown world? We introduce the Algebraic World Model (AWM), a framework that turns interaction with unfamiliar environments into explicit mathematical models supporting formal reasoning. AWM explores the environment and develops executable Python hypotheses, continually testing and revising them against observations. It then structures these hypotheses into typed objects and shared rules, simplifies their structure through category-theory-guided transformations, and formalizes the resulting model in Lean 4 to prove reachability and impossibility. AWM can formally prove that a goal is unreachable, even beyond explored trajectories. On two impossible game levels, it constructs closed, kernel-checked Lean proofs excluding every legal winning sequence in all six runs, while Claude Opus 5.5 and GPT-6 Astra, equipped with coding tools, produce none in twelve baseline runs. Four of AWM's six initial bounds are correct, compared with one for Opus 5.5 and none for GPT-6 Astra; given only feedback that a cheaper win exists, AWM revises its rules and constructs new proofs, reaching six of six correct bounds. Moreover, AWM produces interpretable mathematical models whose rules can be inspected and tested step by step. Across all 25 public ARC-AGI-3 games, these models enable Lean to replay the winning trajectories of all 183 levels and generalize beyond observed play, predicting unseen transitions and detecting changes in game mechanics. With Claude Opus 5, AWM clears all levels with a score of 99.9, while its certified winning trajectories use only 43% of the human baseline's actions.
Conventional wheel-equipped quadrotor UAVs must tilt their bodies to generate lateral forces, limiting their ability to maintain a desired attitude during lateral motion. This paper proposes a wheeled quadrotor with all-clockwise tilted rotors that uses surface contact as a constraint to generate propulsion along the contact surface without tilting the vehicle. We analyze feasible forces and system controllability under surface contact and optimize the vehicle design considering different rotor-spin configurations. The optimization results show that a configuration in which all four rotors spin clockwise can generate a larger tangential force than the conventional alternating-spin configuration. This approach enables both aerial and contact-based locomotion without additional rotor-tilting actuators or mechanisms. Simulation results demonstrate both hovering in free space and horizontal locomotion on a floor while maintaining a level attitude.
We study high-dimensional integration on bounded convex domains. Given a non-negative integrand $r$, the goal is to estimate $Z=\int_{D}r(x)\,\mathrm dx$ on $D\subset\mathbb R^d$. Standard Quasi-Monte Carlo does not adapt its evaluation points to the integrand, while effective importance sampling requires a proposal that captures its concentration. Learned diffusion samplers can supply such a proposal, but existing methods are formulated on $\mathbb R^d$ and do not respect the domain constraint $x\in D$. We instead build the proposal from reflected dynamics that stay in $D$ by construction. A reflected diffusion progressively transforms the target distribution toward the uniform distribution on $D$, and a neural score model is trained to reverse this process. A change-of-measure formula for reflected diffusions yields a training objective without additional boundary terms and an unbiased importance-sampling estimator of $Z$. For non-smooth integrands, where reparameterization gradients may be undefined or uninformative, we derive a REINFORCE estimator of the training gradient using Gaussian proposal densities before reflection, without evaluating reflected transition densities or differentiating $r$. We evaluate on numerous synthetic targets and real-world problems, demonstrating strong performance of the proposed method, as well as favorable scaling with the dimension of the problem and the number of points used for the Monte Carlo estimate.
We present LucidLyra, a framework that makes generatively reconstructed 3D scenes directly queryable for semantics and instances in a feed-forward manner from video latents. While generative 3D reconstruction can synthesize virtual environments from a single image, downstream applications in robotics and physical AI require not only visual realism but also access to scene semantics and object identities. Existing 3D understanding approaches, however, require captured multi-view scenes, have limited generalization capabilities, or rely on expensive per-scene processing and optimization. To bridge this gap, our method distills complementary knowledge from a camera-controlled video diffusion model and frozen 2D vision foundation models into a unified model to jointly infer 3D Gaussians encoding geometry, appearance, open-vocabulary semantics, and class-agnostic instance cues. The resulting scenes support novel-view rendering, open-vocabulary segmentation, and object grouping without per-scene optimization, while training requires neither manual 3D annotations nor captured multi-view data. Our method outperforms baselines combining state-of-the-art 3DGS segmentation approaches with generative 3D scene reconstruction on curated synthetic and real-image-conditioned benchmarks, while preserving reconstruction quality. Furthermore, our latent formulation naturally extends to monocular video, reconstructing structured dynamic 3D scenes across time. By turning renderable but unstructured outputs into queryable 3D worlds, LucidLyra enables downstream applications including 3D scene editing, 3D asset mining, and robotic simulation.
The EGI Federation has provided federated e-infrastructure services to European and global science for over 15 years. We review EGI's early experiences with AI in the interTwin and iMagine Horizon Europe projects, which built digital twins in physics and environmental sciences and an image-analysis platform for aquatic research. We then examine how the AI landscape has changed since 2023 and argue that the focus of AI in science has shifted from model training to adapting and applying AI to specific domains, projects and questions. Building on these lessons, we present the AI strategy emerging from the EGI Federation Strategy 2026-2030, organised around three enablers: (1) an AI-ready infrastructure connecting compute, data and application resources across the continuum; (2) human skills to know what is possible with AI and how to implement it; and (3) trust, to run AI with confidence even in high-risk environments. We describe the projects implementing each enabler, including federated LLM inference, AI-ready data platforms and AI competence centres, and discuss a division of labour with EuroHPC's AI Factories, RAISE, research infrastructures and EOSC, in which EGI specialises in the customisation and long-term operation of AI for research.
The HiLumi LHC, the SKA Observatory and LOFAR 2.0 will take High Energy Physics (HEP) and Radio Astronomy (RA) towards exabyte-scale data within the next decade, beyond the capacity of today's infrastructure. The SPECTRUM project responded with two documents built on the same evidence. A Technical Blueprint describes a European compute and data continuum as a capability map, consolidates the gaps found in HEP, RA and related use cases, and recommends technical actions in eight areas. A Strategic Research, Innovation and Deployment Agenda (SRIDA) organises thirteen priorities in four pillars, maps them to investment areas and European funding instruments, and phases them over a roadmap set against the timelines of the three instruments. This paper, by editors and contributors of both documents, summarises them, their consultative method and the impact the SRIDA expects.
提出一种以学习者参与为核心的多智能体组织框架,并在 Agentic University 中实现,用可修订的“能力项目”把个人目标、学习活动与分层评估串联起来。
cs.AI · cs.CL
查看原文摘要
Large language models support personalized tutoring, content generation, and adaptive learning paths. However, capability development requires these resources and interactions to form a coherent learning process that evolves with the learner. A central challenge is to align goals, activities, and assessment while using learning evidence to decide what should follow. We introduce Human-Participatory Multi-Agent Organization and instantiate it in Agentic University (AU). In AU, learners participate as organization members and work with specialized agents to maintain a revisable Capability Program. The program connects personal goals, learning activities across modalities, and layered assessment, while learner feedback and performance guide subsequent support. Our evaluation shows advantages in program organization, assessment design, and revision quality. Users achieved larger mean assessment gains (12.19 versus 5.61 points on a 50-point scale) and reported stronger cognitive support. This work contributes an organizational approach to adaptive learning that makes learner participation a continuing basis for multi-agent coordination. The Agentic University project is available at \href{https://github.com/AgenticOrgLab/AgenticUniversity.git}.
Quantum error correction is essential for fault-tolerant quantum computing. High-rate quantum low-density parity-check (qLDPC) codes have emerged as a promising approach to reducing the substantial physical qubit overhead of quantum error correction, enabling encoding rates exceeding $1/2$ in blocks of approximately one thousand physical data qubits. However, their practical implementation requires decoders that combine high accuracy with low latency to keep pace with quantum hardware. Existing decoders of high-rate qLDPC codes can achieve high accuracy but often incur substantial computational latency, whereas neural network decoders have yet to be demonstrated for high-rate qLDPC codes. Here, we introduce \emph{neural triage decoding}, a framework that uses syndrome consistency to adaptively allocate neural computation. A local neural message-passing network rapidly predicts error corrections, additional iterations reduce residual syndrome violations, and a rarely invoked diversification stage searches for consistent corrections to the remaining shots. We demonstrate that the \texttt{Triage} decoder can decode ultra-high-rate qLDPC codes encoding a few hundred logical qubits, including lifted-product and Kasai codes, achieving state-of-the-art accuracy comparable to the near optimal algorithmic decoders while reducing decoding latency by approximately one to two orders of magnitude. Our framework is inspired by a rigorous analysis of the exact bitwise marginal decoder, revealing a distance-independent syndrome-inconsistent error floor. In addition, we show the robustness of neural network decoders to mismatched error priors. Our results establish adaptive neural decoding as a promising route towards fast, accurate, and scalable quantum error correction in the near term.
Do research agents have taste, the judgment of which experiments are worth running before their outcomes are known? We give six frontier models seven recent NLP papers. Each model, working as a research agent alone or as a team, proposes minimum viable experiments (MVEs), forecasts whether each will pass a threshold it sets and ranks them. A separate executor then attempts every MVE, including those ranked last, and three model auditors judge the results. Of 415 MVEs, 194 are judged sound, valuable and new, but fewer than half of these (73) are also judged beyond the seed paper and non obvious. The agents' first choices match the auditors' most valued experiment more often than a random pick, but are not shown to improve on choosing the experiment written first. Their forecasts beat a base rate but are not measurably more accurate than those of a fresh instance of the same model given only the paper and registrations. Teams cost more without a clear overall improvement in proposal quality. The agents produce many worthwhile experiments, but the evidence that their rankings improve the choice of which to run remains limited. The evaluation harness and a dataset of all 415 MVEs, with their forecasts and audited outcomes, are available at https://github.com/ArtKanke/rTaste.
An image's original dimensions, aspect ratio, and composition provide important cues that can affect its technical and aesthetic quality. Image assessment methods use resizing, cropping, padding, or patch sampling to accommodate different input sizes. However, these operations can alter or obscure original geometric and compositional cues. Existing assessment models also encode rich multi-level visual evidence that can be further extracted and exploited to improve existing models. This motivates us to combine visual evidence with original-image geometry for score refinement without changing the original scoring pipelines. In this paper, we introduce MetaRefine, a metadata-aware score refinement architecture whose lightweight residual heads predict score corrections from geometry, multi-level visual features, and the frozen model's original score. Across 100 configurations on 21 datasets, MetaRefine improves PLCC in 88 configurations and SRCC in 85, with average relative gains of 7.55% and 7.10%, respectively. It reduces MAE in 90 configurations and RMSE in 89, with average relative reductions of 23.27% and 21.93%, respectively. The median parameter overhead is only 1.11%. MetaRefine can further improve state-of-the-art (SOTA) assessment models on multiple benchmarks.
In this note, we prove that for a subset $\mathcal{F}$ of $\{0,1\}^n$ of density $\frac{1}{8}$, its average pairwise Hamming distance is at least $\frac{n-3}{2}$, with equality attained only by $(n-3)$-dimensional subcubes. This answers a question of Lei Yu, and solves an important open case of a more general question posed by Ahlswede and Katona in 1977.
The Precision Wall: An Optimizer-Dependent Boundary for Optimization under Power-Law Measurement Spectra
Lngel Kyo
AI 速读 基于摘要
在幂律测量协方差下,一阶优化器因数值精度墙在临界指数处停滞,作者提出并验证了预测该边界的公式。
cs.LG
查看原文摘要
In low-rank matrix sensing of a rank-$D$ factor $U^\ast \in \mathbb{R}^{V \times D}$, replacing isotropic Gaussian designs with power-law measurement covariance $Σ= \mathrm{diag}(j^{-s})_{j=1}^V$ leaves the Burer--Monteiro landscape free of spurious local minima, yet division-normalised first-order optimizers stall above a critical exponent $s^\ast$. We trace this failure to a numerical precision wall. At the ground truth, the smallest non-gauge expected Hessian eigenvalue scales at leading order as $V^{-(s+1)}D^{-s}$. When this curvature drops below the effective denominator floor $ε_O$ of optimizer $O$, normalisation noise overwhelms rare-direction gradients, yielding the leading-order boundary $s^\ast_O(V, D) = [\log(1/ε_O) - \log V]/\log(VD) + δ_O$, where $δ_O$ is a metric-dependent detection lag. With $δ_{\mathrm{Adam}}$ calibrated on four configurations and frozen, this formula predicts Adam's onset within $0.45$ across all 16 cells of a held-out grid ($V \in \{64,128,256,512\} \times D \in \{4,8,16,32\}$), separates fixed-$VD$ pairs, and distinguishes denominator-precision walls from conditioning and sign-quantisation walls. The approximation fails at $D = 2$, reflects a finite-$D$ spectral crossover, and saturates below $\varepsilon_0 = 10^{-8}$ at a dynamical floor.
The determinantal complexity of a polynomial is the order of the smallest matrix whose entries are polynomials of degree at most one and whose determinant equals the polynomial. A lower bound for the permanent in this measure is the algebraic form of the question whether the permanent is harder to compute than the determinant. Over the complex numbers, the best known lower bound grows cubically in the size of the permanent. It holds even when the permanent only has to be a limit of such determinants. I prove that the cubic lower bound holds over every algebraically closed field of odd characteristic $p$, with a constant that depends on $p$. Hence the cubic bound does not depend on characteristic zero. I also prove the bound for Pfaffians, which are square roots of determinants of skew symmetric matrices. Lower bounds for Pfaffians imply the same bounds for determinants. Further, I prove the bound, divided by $a$, for matrices whose entries are polynomials of degree at most $a$. All three results come from one lower bound for smooth hypersurfaces. I prove it in every characteristic by counting intersection points together with their multiplicities.
Unlearning concerns the task of removing the influence of a sensitive portion of the training data, such as protected, copyrighted or private text, from a model without retraining it from scratch. While unlearning requests happen continuously during a model's lifetime, the vast majority of LLM unlearning methods are ill-suited for iterated removal, yielding steep decay in forgetting and utility upon sequential unlearning. This decay stems from interference between successive updates, as each new deletion can undo earlier ones or push the model further along directions already degraded by them. To address this, we introduce Continual Orthogonal Projection (COP), a gradient-projection scheme that restricts each update to the orthogonal complement of activation subspaces cached from prior forget sets. This approach provably guarantees first-order non-interference with earlier deletions. COP stores only a low-rank basis per layer, requiring neither past gradients nor previous forget sets, and plugs into unlearning methods that update the model through gradient steps on a differentiable loss without modifying its objective. Experiments on standard LLM unlearning benchmarks (TOFU and RWKU) show that COP preserves utility across sequential requests without weakening forgetting, preventing the collapse of standard objectives and forgetting more effectively than continual-specific baselines.
We propose a novel quantum algorithm for solving linear optimization problems by quantum-mechanical simulation of the central path. While interior point methods follow the central path with an iterative algorithm that works with successive linearizations of the perturbed KKT conditions, we perform a simulation working directly with the nonlinear complementarity equations. Using a two-stage quantum eigenpath traversal schedule, this approach yields an algorithm for solving linear optimization problems involving $m$ constraints and $n$ variables to $\varepsilon$-optimality using $\widetilde{O}\!\left((m+n)^{3/2}\,\varepsilon^{-1}+(m+n)^{1/2}\,\varepsilon^{-3/2}\right)$ queries to an oracle that evaluates a potential function. In the standard gate model (i.e., without access to quantum RAM), our algorithm can obtain $\varepsilon$-precise solutions to LO problems using at most $$\widetilde{O}\!\left(\left[\frac{(m+n)^{3/2}}{\varepsilon} + \frac{(m+n)^{1/2}}{\varepsilon^{3/2}}\right] \cdot \mathrm{nnz}(A)\right)$$ elementary gates, where $\mathrm{nnz}(A)$ is the total number of non-zero elements found in the constraint matrix.
Financial AI workflows that reuse investor knowledge need persistent memory that integrates observations across sources and periods without losing identity or provenance. In a knowledge graph, recurring observations may use different surface forms, fragmenting relationship histories and preventing evidence from accumulating. We introduce Fusion and Identity Registry for Memory Evolution (FIRME), a registry-anchored memory graph that reconciles incoming observations to persistent canonical relationships and retains their source, time, and context. Within periods, rule-based fusion links investor-call discussions to portfolio cash-flow signals, directly or through a fixed product-topic ontology. Across periods, canonical identities and persistent aliases direct recurring observations to the same relationship history; deterministic updates summarize reinforcement, inactivity, and reactivation. We evaluate FIRME on proprietary investor-call and cash-flow records and on S&P 500 earnings-call transcripts. Compared with a historical registry that retains canonical identities and semantic fallback but omits alias memory, FIRME increases final-period Correct Match Rate by 7.8-12.1 percentage points across four dataset-backend settings under a fixed-judge and fallback-review protocol. A blinded human audit of 200 incoming observations per setting finds Correct Match Rate gains of 9.0-16.5 points and reattachment-recall gains of 22.5-29.0 points, with higher observed merge precision in all four samples. A separate audit finds valid evidence paths for 293 of 300 outputs from full within-period fusion in the investor-call setting. Extraction-faithfulness and round-trip diagnostics assess source grounding and preservation of extractor-derived graph content.
Recent advances in interactive world models have made it possible to generate controllable, dynamic environments from action inputs. Yet current models struggle to maintain coherence beyond roughly one minute of rollout, a limitation rooted not in model capacity but in the scarcity of long-horizon training data. Existing gameplay video datasets typically consist of clips under ten seconds, with captions that describe whole clips in coarse and undifferentiated text, which is insufficient for controllable long-horizon generation. We address this with GameVerse, a minute-scale gameplay video dataset purpose-built for long-horizon interactive world modeling. GameVerse contains 69.7K clips spanning 1,655 hours and 349.6 million frames across diverse first- and third-person gameplay, including 1,358 hours of continuous two-minute sequences, an order of magnitude longer than prior datasets. Clips pass through a unified pipeline of scene-consistent segmentation, quality filtering, camera pose estimation, and event-based caption annotation. Each clip is paired with a temporally stable camera trajectory that remains coherent across minutes, together with captions that separate static scene context from dynamic foreground events and align to event boundaries rather than fixed time windows. Comprehensive analysis shows that GameVerse surpasses existing public datasets in scale, diversity, and annotation quality. Experiments further demonstrate that training on GameVerse substantially extends the temporal horizon of interactive world models.
Audio-visual instance segmentation (AVIS) segments and tracks individual sound-producing objects in videos. Existing benchmarks predominantly use monaural audio, which lacks inter-channel cues for spatially distinguishing concurrent sound sources. We introduce AVPS-360 (Audio-Visual Person Segmentation 360), a spatial audio-visual benchmark bridging AVIS and sound event localisation and detection (SELD). Built upon STARSS23, it pairs first-order Ambisonics audio with synchronised 360° video across 230 recordings totalling 10.5 hours. Recordings average 164.0 seconds. The dataset captures intermittent sound production in real-world interactions dominated by speech, alongside laughter, clapping, and footsteps. It provides 31,678 manually reviewed instance masks linked to source identities and sound-event labels. We also present a baseline that integrates spatial audio with visual features for frame-level segmentation and identity association across frames. Experiments on AVPS-360 show that existing AVIS methods struggle with detection and identity association in long recordings with intermittent sound production, while our baseline substantially improves performance in both aspects.
State-of-the-art deep reinforcement learning (RL) methods have achieved remarkable performance in continuous control tasks, yet their computational complexity is often incompatible with the constraints of resource-limited hardware, due to their reliance on replay buffers, batch updates, and target networks. The emerging paradigm of streaming deep RL addresses this limitation through purely online updates, achieving strong empirical performance on standard benchmarks. In this work, we propose two novel streaming deep RL algorithms, Streaming Soft Actor-Critic (S2AC) and Streaming Deterministic Actor-Critic (SDAC), explicitly designed to be compatible with state-of-the-art batch RL methods, making them particularly suitable for on-device finetuning applications such as Sim2Real transfer. Both algorithms achieve performance comparable to state-of-the-art streaming baselines on standard benchmarks without requiring tedious per-environment hyperparameter tuning. We further investigate the batch-to-streaming transition, showing that a naive transition does not guarantee preservation of pre-trained policy performance, and propose a principled approach to address this challenge.
Standardized uptake value ratio (SUVR) quantification of amyloid PET commonly relies on a subject-specific T1-weighted MRI, yet a usable MRI is not always available. We therefore combined CT-to-MRI synthesis with conformal prediction for MRI-free PET quantification with reliability assessment. A slice-consistent Brownian Bridge Diffusion Model was strengthened with multi-dataset training and data-source conditioning to enrich the anatomical prior learned from MRI, and with expanded multi-slice CT context to exploit the through-plane continuity of subject-specific anatomy in CT. Synthetic MRI was used for FreeSurfer-based anatomical parcellation and PET quantification, while deep-ensemble uncertainty was calibrated with conformal prediction to estimate a plausible range for the corresponding real MRI-based SUVR. On $^{11}$C-PiB PET from OASIS-3, the proposed method achieved the highest synthesis and parcellation fidelity among the compared methods. Mean cortical SUVR from the proposed synthetic MRI agreed closely with the real MRI-based reference (MAE $0.016 \pm 0.015$, Pearson $r = 0.9987$) and yielded the same amyloid-positivity classification as the real MRI in all 87 test subjects at the prespecified cut-off. Conformal prediction achieved empirical coverage close to the prespecified levels, and at 90% target coverage, 85 of 87 subjects had prediction intervals that supported an unambiguous amyloid-positivity decision. Zero-shot evaluation on an independent external cohort showed that the proposed CT-to-MRI model could support PET quantification without retraining, although conformal calibration required target-cohort recalibration to recover the intended coverage. These findings support CT-to-MRI-based MRI-free PET quantification as a promising approach for providing accurate SUVR measurements and an explicit assessment of their reliability.
Service orchestration across the edge--cloud continuum increasingly uses language models (LMs) to translate intents and operational evidence into scheduling, configuration, diagnosis, and remediation decisions. Yet, useful model outputs do not by themselves establish dependable orchestration: reliability also depends on where the LM enters the decision process, what authority it is granted, how actions are constrained, and what system-level evidence supports the claimed effect. Existing surveys provide limited synthesis of the links between continuum-specific orchestration decisions, LM responsibility, operational authority, assurance controls, and supporting empirical evidence. We systematically review 39 primary studies and develop a five-dimensional analytical framework for connecting system context, orchestration decisions, LM agency, operational safeguards, and evaluation evidence. The synthesis reveals predominantly hybrid designs in which LMs support interpretation, candidate generation, and mitigation planning, while downstream components commonly retain feasibility enforcement and execution authority. Bounded closed-loop remediation is emerging, but continuum-specific constraints remain unevenly represented in decision formulations, and production-scale evidence across heterogeneous edge--cloud environments remains limited. These findings suggest that reliance on LM-enabled orchestration depends on aligning decision constraints, operational authority, safeguards, and evaluation evidence with the claimed system effect.
In psychiatric practice, the clinical intake interview remains a primary diagnostic instrument, requiring the clinician to establish rapport while disentangling complex, overlapping presentations. Here, we show that multi-turn reinforcement learning (RL) in simulation environments improves language model performance on structured text-based psychiatric intake, spanning history-taking, differential diagnosis, and initial management planning. In a randomized, double-blind crossover study ($N = 60$ matched scenario pairs, 120 encounters) comparing the RL-trained agent against its identically prompted base model, 32 board-certified psychiatrists role-played standardized patients while a separate panel of 15 independent, board-certified psychiatrists scored the de-identified transcripts. The trained agent outperformed the base model in 76.7% of matched scenario pairs ($p < 0.0001$), with gains on an adapted clinical-examination rubric ($d_z = 0.77$, $p < 0.0001$), patient-centered communication (82.0% vs. 65.2%, $p < 0.001$), and differential diagnosis appropriateness (68.3% vs. 33.3%, $p < 0.001$). Across 127 psychiatrist-validated simulated intake scenarios, the trained agent nearly doubled its base model's clinical rubric score (0.706 vs. 0.379; composite reward 0.564 vs. 0.294, $p < 0.0001$). To systematically probe conversational safety, we established two Delphi-consensus taxonomies, of clinical safety risks and relational competencies, from which 256 challenging adversarial presentations were derived; we find that training in simulation environments more than halved under-triage of acute safety risks (12.9% vs. 30.5%, $p < 0.0001$). Simulation environments thus provide a controlled testbed for training and stress-testing psychiatric conversational agents, with gains that transferred to psychiatrist-enacted encounters, though residual gaps require safeguards and clinician oversight.