This paper proposes a method to estimate normal and shear pressures in prosthetic sockets using sparse sensing and mechanical models. By validating with global wrench and local interface loads, a quasi-static spring-mass contact model with least-squares parameter identification reduces measurement offsets, offering objective fit metrics.

This paper presents DLO-Lab, a differentiable simulator designed for deformable linear objects (e.g., ropes, cables, rubber bands). It models a wide range of material properties, provides a benchmark suite of tasks, and introduces a specialized agent to handle topological complexity and grasp sensitivity. Various policy-learning algorithms are evaluated, with sim-to-real transfer experiments.

This paper proposes a risk-aware model predictive control (RA-MPC) framework that incorporates prediction sets to guarantee risk control below a user-specified threshold without assumptions on the uncertainty distribution. By extending conformal risk control to general spectral risk measures, it achieves distribution-free risk quantification. Simulated vehicle obstacle avoidance scenarios demonstrate improved safety and reduced solve time compared to a baseline RA-MPC framework.

This paper presents Affordance2Action (A2A), a benchmark-centered learning framework for scene-level, task-conditioned part affordance grounding. Its core is A2A-Bench, a manipulation-oriented benchmark covering single-region and multi-region instruction correspondences in everyday scenes. Built with the A2A-AffordGen annotation pipeline, experiments show A2A exposes gaps in existing methods and improves task-level localization for downstream manipulation.

This paper proposes a distributed, risk-aware multi-agent NBV framework where each robot maintains a private local 3D Gaussian Splatting map and jointly maximizes expected information gain via Consensus ADMM, reducing communication by orders of magnitude while maintaining mapping quality and safety.

This study compares three haptic guidance models—spring-damper, potential field, and guiding tube—in teleoperation tasks. No universal best model is found: spring-damper excels in cluttered environments, potential field works well in free space but risks near obstacles, and guiding tube offers a balanced compromise. New objective metrics are proposed, showing that guiding force magnitude correlates with comfort and trust scores.

CLAW is a fully end-to-end self-supervised framework that learns world models and continuous latent action representations from action-free videos using adversarial latent regularization and diffusion-based generation. It enables imitation learning from observation and goal-directed planning, outperforming existing methods.

AgenticDiffusion is a multi-view UAV navigation framework that coordinates language-guided reasoning, open-vocabulary target grounding, vision-based diffusion planning, and NMPC. In 40 real-world trials, it achieved an 80% mission success rate and 100% trajectory generation success.

The paper introduces Spatial Artifact Coherence (SAC), a metric measuring when patch-based rPPG outperforms global methods under codec compression. Experiments on 280 subjects across 11 codec variants show SAC explains 93.8% of PCA advantage variance. Non-MPEG-4 codecs (SAC 0.10-0.18) achieve 84-90% PCA win rates, while MPEG-4 (SAC 0.48-0.59) only 61% with 5.8x reduction in improvement. P-Hybrid is identified as the most robust algorithm, with PatchPCA advantage requiring SAC<0.30 and low-to-moderate motion.

A new benchmark, GroupToM-Bench, evaluates multimodal large language models on group-level theory of mind. While models excel at individual mental state reasoning, they fail at understanding collective behavior that emerges nonlinearly from social tensions and structural constraints. The benchmark covers a causal chain from micro-level beliefs, desires, and intentions to group tension and macro-level outcomes, using a seven-level cognitive audit. Experiments reveal a significant gap between current models and human baselines.

This paper introduces Orli (Ordered Regression of Lines), an end-to-end model that unifies text line detection and reading order prediction as a single image-to-sequence task. Trained on 196,691 pages across ten writing systems, Orli marginally exceeds state-of-the-art on cBAD line detection without dataset-specific training, achieves near-perfect coverage and ordering on multiple reading-order benchmarks zero-shot, and adapts to specialized out-of-domain layouts with limited fine-tuning. Code and weights are open-sourced.

Pinpoint is a new image geolocation method that combines internet photos and street-view imagery using a retrieve-and-rerank architecture. It trains a contrastive embedder on both Flickr and street-view data to learn a shared image-GPS space, then uses an attention-based reranker to rescore candidates. Without relying on multimodal LLMs, it achieves state-of-the-art results on multiple benchmarks.

A diffusion model fine-tuned for single-image reflection separation, jointly generating transmission and reflection layers with a cross-layer self-attention mechanism and disjoint sampling strategy, achieving state-of-the-art performance on real-world benchmarks.

A new benchmark, EVID-Bench, assesses search-based video misinformation detection. It includes 222 videos with 9 manipulation types in 3 categories. The best model achieves only 61.43% point-level and 43.24% video-level accuracy, with AI-generated manipulations being especially challenging.

This paper proposes a new approach to optimal transport flow matching by treating the prior as a design choice rather than a fixed input, avoiding the intractable computation of OT coupling in high dimensions. The authors identify low-frequency projection of natural images as a prior that admits an OT-optimal identity coupling with data, reducing the flow matching task to synthesizing high-frequency details. The method requires no modifications to the flow model and integrates naturally with latent-space models, classifier-free guidance, and one-step generation frameworks. Across benchmarks, trajectory curvature is reduced by more than 2x, improving generation quality in the few-step regime.

This paper proposes IN2R, a novel framework that shifts from discrete selection to synthesizing continuous soft prototypes to rectify noisy correspondence in cross-modal retrieval, leveraging the geometric stability of intra-modal data for graph reasoning, achieving state-of-the-art performance on multiple datasets.

The paper proposes SASA, a drift-resilient approach for weakly incremental learning in semantic segmentation. It uses learnable semantic anchors as rigid class-level references and elastic residual adaptation for stable yet flexible representation learning. A Spatial Label Arbitration mechanism filters noisy supervision and enforces the 'one object, one class' constraint. Experiments show state-of-the-art performance on standard benchmarks, especially in challenging multi-step incremental settings.