This paper presents Parallel ARC (P-ARC), a parallel variant of the Adaptive Robot Coordination (ARC) approach to multi-robot motion planning (MRMP). P-ARC proposes a parallel variant for each of the three main stages in ARC: initial individual solutions, conflict detection, and conflict resolution, exploiting the independence created by ARC's decomposition of the MRMP problem. Additionally, we employ an OR-parallel multi-start strategy to both ARC and P-ARC, creating a hybrid parallel strategy OR-P-ARC. We evaluate the impact of the different parallel strategies for ARC using a set of scaling 2D mobile and planar manipulator scenarios with up to 128 robots to control for conflicts and work distribution across the stages of ARC. Additionally, we demonstrate planning time speedups approaching 4X over the sequential version for large Panda multi-manipulator teams in real-world inspired scenarios when deploying 16 CPU cores.

This paper presents an automation framework for robotic radiation source localization (RSL) using physics-informed machine learning (PIML). It enables precise source estimation without requiring the robot to approach the source, reducing radiation damage risk. Physics-inspired tensors handle gamma-ray attenuation from unknown obstacles, and parallel model computation improves robustness. Evaluated via high-fidelity Monte Carlo simulations and physical experiments, the method also incorporates continuous learning for real-world deployment.

A hybrid simulation framework couples a high-fidelity quadrotor model with a physics solver to train an RL policy that, deployed zero-shot on hardware, reduces landing error by 50% and throw duration by 30%. Visual-based policies achieve comparable accuracy.

SceneBot is a unified motion-tracking framework for humanoids that handles free-space locomotion, terrain traversal, and whole-body manipulation. By conditioning a single policy on both reference motions and per-link contact labels, it explicitly defines expected environmental interactions. To address the lack of annotated interaction data, the authors propose a hindsight scene reconstruction approach that infers scene-interaction graphs from retargeted human motion. Trained on 7.5 hours of reconstructed contact-rich data, SceneBot generalizes to unseen motions and environments, enabling complex long-horizon tasks like carrying a box upstairs. It is the first general framework to seamlessly unify free-space and contact-rich behaviors.

Existing fiducial markers are mostly single-scale and designed for terrestrial robotics, leaving the camera's field of view at close range during critical proximity and docking phases. This paper presents AstraTag, a fiducial marker based on a square Spidron pattern with recursive self-similar structure enabling multi-scale detection, 48-bit identification encoded with Generalized Reed-Solomon code, and Thin-Plate Spline re-warp for curved surfaces. Benchmarked on spacecraft mockups, AstraTag achieves higher detection rate on curved surfaces than three-layer Fractal ArUco and AprilTag, offering a robust recursive-marker option for space robotics.

A new anytime multi-robot motion planning method, AO-ARC, achieves initial solution times on par with state-of-the-art feasibility solvers while converging faster and more reliably as the number of robots grows. It adapts the AO-x meta-algorithm by iteratively calling ARC on bounded instances, proving asymptotic optimality.

SCORE framework constrains RL in simulation to the support of a generative policy pretrained on real data, improving manipulation success rate from 37.8% to 89.9% without real-world training.

TTE is a learnable location encoder using Spherical Voronoi partitions to focus capacity on discriminative regions and global semantic tokens for sharing semantics across similar environments, achieving state-of-the-art on geospatial tasks.

This paper introduces Structured-Li-GS, a lightweight Gaussian Splatting pipeline that integrates LiDAR-inertial-visual SLAM. It achieves high-quality 3D reconstructions with fewer Gaussians by training on accurate, dense, colorized point clouds, without requiring Gaussian densification. Multiple loss functions guide the training, producing up-to-scale, high-fidelity results. Experiments on benchmark and in-house datasets surpass state-of-the-art methods.

TruEye is a novel model for fine-grained detection and localization of AI-generated or manipulated humans and scenes, distinguishing among five compositional categories of synthetic content. It runs over 100x faster than LLM-based competitors and outperforms state-of-the-art detectors on multiple datasets.

ReWorld is the first representation learning framework specifically designed for autonomous-driving world action models. It directly optimizes intermediate representations along three dimensions: future-predictive supervision on the generation module, cross-modal alignment and hard-negative supervision on the planning module. Experiments on nuScenes and NAVSIM show significant improvements in video generation quality and closed-loop planning performance, along with faster convergence.

Aloe-Vision introduces a family of open-source medical vision-language models trained on a large-scale quality-filtered dataset, achieving balanced performance and exposing vulnerabilities to adversarial inputs.

DMV-Bench is the first interactive benchmark for multimodal-agent visual memory, built on a home-furnishing e-commerce catalog of 1,000 product variants. Each product image carries a unique incidental cue; agents must recall cued products after long shopping sessions. The proposed DualMem architecture, maintaining parallel visual and verbal codes, outperforms baselines on Gemini 2.5 Flash and Qwen2.5-VL-7B.

SelectAnyTree is a promptable instance segmentation model that segments individual trees from 3D forest LiDAR point clouds with few clicks. It features a click-to-query prompt encoder and a Canopy Height Model-guided first prompt, with a state-space query decoder for efficient long-range context. Evaluated on seven diverse forest regions and a held-out dataset, it achieves 78.2 IoU from a single click, outperforming baselines by 24.8 points.

Researchers fine-tuned Gemini 2.5 Pro on 400 clinician-rated home videos using low-rank adaptation, achieving significant improvements in inter-rater reliability and ASD diagnosis accuracy, matching or exceeding clinician performance. The approach enables scalable behavioral feature extraction for autism assessment.

SemCityLoc is a novel aerial localization method that reframes pose estimation as structured surface registration between foundation-model visual priors and standardized LoD 3D city models. It eliminates reliance on precise GNSS or radiometric 3D reconstructions by aligning semantic surfaces and monocular depth with lightweight building models. The benchmark SemCityLockeD, combining centimeter-accurate UAV poses with LoD1-LoD3 models, is introduced. Experiments show up to 36% recall improvement and mean positional error reduction from 9.89m to 2.62m in urban canyons.

A new framework called Transformation-Aware Decoupling (TAD) improves viewpoint robustness in 3D scene graph generation by decoupling relation reasoning into viewpoint-sensitive and viewpoint-invariant components.

Ultra-fine entity typing (UFET) assigns highly specific types to entity mentions, but struggles with long-tail types due to reliance on sentence-level context. We present Narrative-UFET, which pairs each mention with an automatically generated narrative to provide cross-sentence context. Experiments show consistent improvements on long-tail types, especially when the entity's type changes across the narrative. Synthetic narratives outperform natural contexts, suggesting controlled discourse construction can surface implicit signals.

Ko-WideSearch is a Korean breadth-search benchmark built via an automated synthesize-and-verify pipeline, comprising 228 tables over 190 entities across 16 categories and three difficulty tiers. Evaluations on 20 web agents show consistent failure: agents recover sets but not rows (Item-F1 92.8 vs Row-F1 53.7), accuracy drops with difficulty, and open-ended free-text cells are the main bottleneck.

EntMTP is a training-free scheduler that dynamically switches tree-based attention topologies based on local generation entropy, enabling deep speculation in low-entropy regions and conservative speculation in high-entropy regions. It maximizes throughput without sacrificing quality, achieving 1.15x speedup over Hydra and peak 1.36x over Medusa on various benchmarks.

A new recurrent neural network architecture that pre-contextualizes tokens using a transformer block and correction network, achieving significant speedups over standard transformers while maintaining or improving performance.

Large language model (LLM) agents struggle to update facts in long-term interactions. Replacing full context with bounded memory drops accuracy from 92% to 77% even on frontier models. The gap scales with conversation length, not memory size. The authors introduce Supersede, a reinforcement learning environment that trains agents to prioritize current facts over superseded ones. Fine-tuning Qwen2.5-3B in this environment nearly doubles held-out accuracy (9.0% to 16.7%).

This study uses a developmental approach to investigate the statistical learning and mental representation of neural language models (NLM). A series of Generative Transformer models are trained on a synthetic grammar, and model states are saved at multiple stages. By analyzing changes in internal representations, the authors find that NLMs acquire the most abstract global statistical knowledge at the beginning of learning, and later acquire local statistical dependencies. This learning path contains many over-generalizations from the start, which are gradually constrained later. Based on this observation, a new framework is proposed to explain the statistical learning and language cognition of NLMs.

Team HSA_CORAL presents their submission to the FinCausal 2026 shared task, comparing three model families for cause-effect extraction from financial narratives via QA in English and Spanish. Supervised fine-tuning yielded the best results, with GPT-4.1 Mini achieving top scores on the English subtask and third on Spanish, highlighting the value of multilingual fine-tuning.

This survey systematically reviews automated presentation coaching systems covering pronunciation, fluency, prosody, multimodal, and Q&A tools. It introduces a five-dimensional task taxonomy (segmental pronunciation, lexical stress, suprasegmental prosody, pacing, content faithfulness) and maps surveyed systems to reveal coverage gaps. Core methods include TTS-based exemplar generation and diagnostic assessment. Open challenges include scarcity of annotated corpora, accent-fair feedback, and low-latency real-time diagnostics.

This position paper argues that the term "machine unlearning" is overused in LLM research and should be reserved for dataset-defined deletion. Many tasks currently labeled as unlearning pursue different objectives and require separate terminology and evaluation methods. The authors call for stricter terminology aligned with explicit guarantees and reference models.

Researchers introduce an axiomatic evaluation framework for latent thought representations in LLMs, defining four axioms (Causality, Minimality, Separability, Stability) with quantitative metrics independent of downstream accuracy. Auditing 23 reasoning tasks, they find no candidate satisfies all axioms, representations cannot distinguish questions within the same task, and encode little beyond input embeddings. The failure persists across model families, indicating a structural gap.

This paper presents Privacy-Preserving Probabilistic Race/Ethnicity Estimation (PPRE) to enable fairness measurements with respect to race/ethnicity for U.S. LinkedIn members while preserving privacy. It combines the Bayesian Improved Surname Geocoding estimator with a sparse golden survey set of self-reported demographics, and applies secure two-party computation, differential privacy, and additive homomorphic encryption.

This study evaluates ten reduced-domain boundary treatments for predicting bottom-hole pressure (BHP) and CO2 plume migration in geological carbon storage. Conserving corner pore volume is critical; uniform treatments cause large errors, while corner corrections significantly improve accuracy. The gradual modifier with transmissibility correction performs best, achieving BHP NRMSE below 3.7% and plume IoU above 0.97 in both homogeneous and heterogeneous reservoirs.

A new study shows that activation patching, a key tool in mechanistic interpretability, conflates the natural indirect effect (NIE) with interaction effects (INT), which measure how a component's causal influence depends on other components. This can lead to misattribution of importance and instability in faithfulness scores. The authors demonstrate failures in GPT-2's IOI circuit, prove INT is inevitable but useful as a diagnostic, and show it scales with activation distance and decomposes into pairwise and higher-order interactions.