Noticias e Investigación

arXiv:2605.23888v1 Announce Type: new Abstract: We introduce a new approach to high-fidelity 3D scene reconstruction from multi-view RGB images that tightly couples reconstruction with a strong generative 3D prior. We cast scene reconstruction as conditional 3D generation over a set of spatially-localized, overlapping chunks that together tile the scene, scaling generation to large scene extents. Crucially, we inherit the fidelity and completeness of state-of-the-art generative shape models -- we use Trellis.2 as an example -- which we generalize to the scene level. To this end, we propose a projection-based conditioning mechanism that lifts posed multi-view image features into a coherent 3D representation aligned with the generative model, independent of view ordering and spatially anchored to the scene, yielding high-fidelity, multi-view consistent generated geometry. This enables lifting the strong object-level prior of Trellis.2 to multi-view, scene-scale generation, producing fait

arXiv:2605.22824v1 Announce Type: cross Abstract: Environmental monitoring is a crucial component of the smart city infrastructure. It enables informed decision making which enhances sustainability, public health and urban planning. However, the large-scale deployments of the smart sensors have raised concerns on excessive energy consumption and redundant data collection as well as limited sensor lifespan. To resolve these issues, we present an AI-driven framework for energy-efficient environmental monitoring in smart cities utilizing edge intelligence. Our proposed framework leverages TinyML-enabled edge devices and context-aware adaptive decision-making in order to dynamically activate the sensors based on the spatiotemporal conditions, environmental statistics and energy constraints. The sensors will be dynamically activated based on a utility function that takes in factors such as real-time environmental conditions, sensor location, and remaining battery lifespan. Our framework wil

arXiv:2605.23540v1 Announce Type: new Abstract: Dimensionality Reduction (DR) methods are widely used to visualize high-dimensional data. One key task in DR-based analysis is discovering neighborhoods, which relies on analyzing the fine-grained local structure of a projection. However, DR is an inherently lossy process; no technique can perfectly preserve the high-dimensional relationships, and projections therefore contain visual artifacts. In this paper, we highlight a typically overlooked source of visual artifacts: ambiguous instances. These are instances that are highly similar to multiple mutually dissimilar neighborhoods in the high-dimensional space. Standard DR methods cannot faithfully project such instances, since each data instance is mapped to a single point in the visual space. As a result, such an instance is placed in only one of its neighborhoods (or in none at all), so only part of its neighborhood structure is represented. We call this distortion partial neighborhood

arXiv:2512.15436v2 Announce Type: replace-cross Abstract: We introduce an extension of the partitioned local depth (PaLD) algorithm that is adapted to online applications such as semi-supervised prediction. PaLD is best known for unsupervised, parameter-free clustering, but its robustness is based on triples of data points, making exact analysis computationally expensive. Research is ongoing to improve the scalability of the underlying discrete algorithm and expand the breath of PaLD's applications. The new algorithm we present, online PaLD, is well-suited to situations where it is possible to pre-compute a cohesion network from a reference dataset. After $O(n^3)$ steps to construct a queryable data structure, online PaLD can extend the cohesion network to a new data point in $O(n^2)$ time. Our approach complements previous speed up approaches based on approximation and parallelism. In practical terms, online PaLD makes larger datasets accessible to exact analysis with a relatively sim

arXiv:2605.21071v3 Announce Type: replace-cross Abstract: The rapid progress of large language models (LLMs) is shifting semantic search toward a question-answering paradigm, where users ask questions and LLMs generate responses. In high-stake domains such as law, retrieval-augmented generation (RAG) is commonly used to mitigate hallucinations in generated responses. Nonetheless, prior work shows that RAG systems, whether general-purpose or legal-specific, still hallucinate at varying rates, making fine-grained evaluation essential. Despite the need, existing evaluation frameworks for legal RAG systems lack the granularity required to provide detailed analysis of retrieval and generation performance separately. Moreover, current benchmarks are largely English-only and centered on legal expert queries, overlooking non-expert needs. We introduce ClaimRAG-LAW, a comprehensive dataset for legal RAG that supports French and English, targets both experts and non-experts, and includes diverse

arXiv:2604.21502v2 Announce Type: replace Abstract: Real-world weather, illumination, and imaging variations often induce severe domain shifts, degrading single-source detectors in unseen environments. Existing single-domain generalized object detection (SDGOD) methods mainly rely on data augmentation or domain-invariant learning, while largely overlooking how domain shift disrupts detector prediction stability. Through analytical experiments, we find that performance degradation is mainly dominated by increasing missed detections. Further analysis shows that this phenomenon stems from reduced cross-domain stability in DETR-style detectors: domain shift disrupts encoder-side object-background and inter-instance relations, and further weakens the semantic-spatial binding between decoder queries and real objects. Motivated by this, we find that vision foundation models (VFMs) still preserve stable relational structures and object responses under severe shifts, making them suitable cross-

arXiv:2602.20102v2 Announce Type: replace-cross Abstract: Despite the strong performance of large language models (LLMs) across diverse tasks, their susceptibility to adversarial attacks and unsafe content generation remains a significant obstacle to deployment, particularly in high-stakes settings. Addressing this challenge requires safety mechanisms that are both practically effective and theoretically grounded. In this paper, we introduce BarrierSteer, a novel inference-time framework that improves response safety by embedding learned nonlinear safety constraints directly into the model's latent representation space. BarrierSteer treats hidden-state safety classifiers as Control Barrier Functions (CBFs), enabling constraint-guided steering of unsafe latent trajectories during generation. By composing multiple safety constraints through efficient constraint merging without modifying the underlying LLM parameters, BarrierSteer preserves model utility. We provide theoretical results sh

arXiv:2605.23177v1 Announce Type: cross Abstract: Large language models (LLMs) have the potential to boost human productivity by speeding up task completion -- provided users know when to offload cognitive work to them. But we do not know if users are well-calibrated in estimating these potential time savings. We conducted a preregistered large-scale behavioral study (N = 1237) to characterize mismatches between expectations and reality, with a focus on simple cognitive tasks. While actual completion times between independent completion and AI-assisted completion did not differ, participants predicted AI to be significantly faster. The same bias was not observed when imagining help from another human participant. We identify a speedup illusion where people have accurate forecasts of independent completion times but significantly underestimate AI-assisted times. Additionally, time and effort dissociate: participants reported lower subjective effort with AI despite equivalent completion

arXiv:2605.23241v1 Announce Type: new Abstract: Relational databases (RDBs) remain the cornerstone of modern data systems and support diverse predictive tasks. Recent relational deep learning (RDL) methods enable end-to-end prediction by converting RDBs into graphs, where rows are represented as nodes and inter-table interactions are represented as edges, and then applying graph-based models for representation learning. Despite the strong capability of RDL, effective self-supervised pre-training for RDBs remains non-trivial. RDB tasks often require multi-faceted information across different perspectives and granularities. For example, user churn classification may rely more on interaction patterns, whereas consumption value prediction requires both user-item behaviors and intrinsic user attributes for fine-grained regression. Such heterogeneous needs challenge RDB representation learning, as pre-training objectives should cover comprehensive information for downstream adaptation. Howev

arXiv:2605.23235v1 Announce Type: new Abstract: Globalization and multiculturalism continue to produce increasingly diverse speech varieties. Yet current spoken dialogue systems frequently fail on under-represented dialects and accents, often misidentifying the input language and causing cascading failures in downstream dialogue tasks. Addressing this dialectal variance under low-resource constraints remains an open challenge, as standard fine-tuning is computationally expensive and prone to overfitting on high-dimensional speech data. We propose Convex Language Detection (CLD), a novel framework that integrates theoretically grounded convex optimization techniques into the spoken dialogue systems pipeline. Our method is efficiently implemented via multi-GPU Alternating Direction Method of Multipliers (ADMM) in JAX, thus providing global optimality guarantees and fast training in polynomial time. Theoretically, we prove that our convex objective induces certified margin stability and p

arXiv:2605.23523v1 Announce Type: new Abstract: Reconstructing the motion of objects from videos is a key component for embodied AI and robot manipulation. While diverse approaches to object pose tracking have been studied, they rely heavily on strong external priors, such as depth data or 3D templates, and remain highly vulnerable to severe occlusions by hand grasps despite the use of explicit masks. In this work, we present ComPose, a 6DoF object tracking framework designed for hand-aware object pose estimation from RGB video. Rather than treating the hand purely as an occluder, our method harmonizes hand motions as a \textit{complementary cue} for object tracking. In detail, we recover a variety of object motions over time by combining object and hand cues from foundation models within a unified tracking pipeline. Here, ComPose adaptively selects informative hand joints, combines object- and hand-derived cues for motion estimation, and refines the resulting object motion using visib

arXiv:2604.10077v2 Announce Type: replace Abstract: In Document Understanding, the challenge of reconstructing damaged, occluded, or incomplete text remains a critical yet unexplored problem. Subsequent document understanding tasks can benefit from a document reconstruction process. In response, this paper presents a novel unified pipeline combining state-of-the-art Optical Character Recognition (OCR), advanced image analysis, masked language modeling, and diffusion-based models to restore and reconstruct text while preserving visual integrity. We create a synthetic dataset of 30{,}078 degraded document images that simulates diverse document degradation scenarios, setting a benchmark for restoration tasks. Our pipeline detects and recognizes text, identifies degradation with an occlusion detector, and uses an inpainting model for semantically coherent reconstruction. A diffusion-based module seamlessly reintegrates text, matching font, size, and alignment. To evaluate restoration quali

arXiv:2602.11146v2 Announce Type: replace Abstract: Preference optimization for diffusion and flow-matching models relies on reward functions that are both discriminatively robust and computationally efficient. Vision-Language Models (VLMs) have emerged as the primary reward provider, leveraging their rich multimodal priors to guide alignment. However, their computation and memory cost can be substantial, and optimizing a latent diffusion generator through a pixel-space reward introduces a domain mismatch that complicates alignment. In this paper, we propose DiNa-LRM, a diffusion-native latent reward model that formulates preference learning directly on noisy diffusion states. Our method introduces a noise-calibrated Thurstone likelihood with diffusion-noise-dependent uncertainty. DiNa-LRM leverages a pretrained latent diffusion backbone with a timestep-conditioned reward head, and supports inference-time noise ensembling, providing a diffusion-native mechanism for test-time scaling an

Autonomous robot navigation requires reliable path planning under uncertainty. Classical algorithms such as $\mathrm{A}^{*}$ and Dijkstra's, and sampling methods like PRM/RRT, work well on static, discrete maps but degrade in dynamic, high-dimensional settings. We study reinforcement learning (RL) for this problem, contrasting value-based Q-learning/DQN (effective with discretised motion primitives) with policy-gradient, actor-critic methods that natively support continuous control. We present an actor-critic approach for continuous navigation that uses offpolicy training with experience replay and entropy regularisation (SAC-style) to stabilise learning while producing smooth, kinodynamically feasible commands (linear and angular velocities). Evaluations in a first-person navigation task and an unmanned-driving simulator use success rate, SPL/path-length ratio, collisions and learning curves. Compared with a DQN baseline and a vanilla actor-critic, our method converges faster and more stably, achieving rising episode returns (from −5 to +7 by 10 episodes) and the lowest average training time ($\sim 1300 \mathrm{s}$ versus $\sim 1300-1700 \mathrm{s}$ for DQN and $\sim 2300-2750 \mathrm{s}$ for standard actor-critic). Qualitative rollouts show fewer collisions and smoother trajectories. These results indicate that actor-critic RL is a strong choice for continuous-control navigation, outperforming discrete value-based methods in dynamic environments.

This paper compares the performance of a traditional approach for autonomous robot navigation and a new approach for the same problem, all within the framework of reinforcement learning. A new approach for the problem has been introduced and compared against the traditional approach, referred to as the value iteration approach for holonomic robots and the new approach for the same problem in relation to the traditional approach. These approaches include sampling-based policy estimation and interpolation and optimization-based filtering for obstacle avoidance. Actor critic methods for non-holonomic scenarios include Deep Deterministic Policy Gradient (DDPG) and Soft Actor-Critic (SAC) approaches. The simulation of various 2D and 3D scenarios, ranging from simple to complex, shows that value iteration method convergence occurs rapidly, while at the same time a success rate of over 95% can be attained within 31 minutes of virtual time. DRL techniques, however, succeed in attaining an average of 88.5% ± 4.2% in 300 scenarios, where in each case, 35% faster convergence of SAC compared to DDPG could be attained. The efficacy of reinforcement learning approaches to find practical solutions to robot navigation in various scenarios, while meeting constraints, has been proven.