Evaluating robotic foundation models still relies on expensive closed-loop rollouts in simulation or reality. This paper proposes Sensorimotor Alignment ($S^2$), a training-free offline metric inspired by the Platonic Representation Hypothesis, which scores how well a model's sensory embeddings align with the geometry of recorded end-effector trajectories. The authors find positive correlations between $S^2$ and task success across vision-language-action models, raw vision-language models, world action models, and real-robot policies, and argue the metric can cheaply rank models and diagnose representation-level behavior.

This paper tackles cross-session indoor navigation, where an agent must reach a prior-session goal despite scene changes, sensor differences, and partial overlap. The key idea is a sparse topometric graph whose nodes compress local 3D geometry around traversable anchors and whose edges encode traversable distance, enabling both memory-efficient storage and learned graph matching for alignment. The approach matters because it promises to slash map memory by over two orders of magnitude while outperforming dense grids, appearance maps, and semantic graphs on standard benchmarks.

The paper addresses vision-based policy learning for laparoscopic robotic manipulation, where end-to-end RL suffers from sparse visual signals and stringent precision requirements, while imitation learning demands scarce expert demonstrations. The authors propose distilling a privileged state-based teacher into an RGB-based student by matching their Gaussian action distributions, with particular emphasis on theoretically analyzing first- and second-order properties of matching objectives including forward KL, reverse KL, Jeffreys divergence, and Wasserstein distance. Extensive experiments in the SurRoL simulator indicate that uncertainty-aware distribution matching—especially Jeffreys divergence—achieves markedly more stable and higher success rates on complex surgical tasks than general RL or imitation learning baselines.

As populations age, robotics and ambient AI are increasingly proposed to help older adults live independently in private homes and residential aged care (RAC) facilities. This chapter frames both settings as extreme human-robot interaction (HRI) environments—cluttered, dynamic, and technically under-supported—and surveys the sensors, perception algorithms, interaction designs, privacy safeguards, and evaluation frameworks needed to make such deployments viable. Its central thesis is that success requires moving beyond lab accuracy toward real-world operational metrics, privacy-by-design, and sustained acceptability.

Whole-body vision-language-action (VLA) policies for humanoid loco-manipulation usually condition only on the current view, so they fail when brief object cues vanish before the robot must act. This paper proposes WholeBodyMem, which uses a frozen SAM3 to track task objects, detects object events (appear, disappear, move, change shape) to causally select up to $B_{\max}=7$ key frames, and feeds those native tokens together with mask-pooled object tokens into a flow-matching action expert via cross-attention and FiLM. On the new HuMeGo benchmark and standard SIMPLE tasks, the method raises the $\Psi_0$ base policy's simulated success from $29.1\%$ to $72.6\%$ and real-world Unitree G1 success from $36.7\%$ to $88.3\%$, while also improving reactive tasks to $86.9\%$.

This paper asks whether robot learning must rely on embodied data by training in-context action predictors entirely on procedurally generated, non-robotic mathematical abstractions—tabular MDPs, contextual bandits, and linear dynamical systems. Using a Prior-Data Fitted Network framework, the authors show that these synthetic control priors achieve non-trivial zero-shot action prediction on held-out simulated and real-world robots, including manipulators, wheeled vehicles, quadrupeds, and aerial platforms. The work matters because it cheaply decouples structural prior acquisition from expensive physical data collection, offering a scalable complement to embodied foundation model pipelines.

Inside-JEPA tackles the opacity of latent world models by embedding relational channels for ordered entity pairs directly into the JEPA latent state. The core idea is that an inverse-dynamics loss—recovering actions from changes in these channels—can ground them to geometric relations without any relation labels during training. This matters because it could let world-model states be read and given goals in relational terms, the natural vocabulary for planning and manipulation.

FocusVLA targets a subtle but important failure mode in multi-view Vision-Language-Action models: policies tend to develop early visual preferences—especially over-reliance on wrist cameras—and persist with them even when task stages shift toward global planning. The paper proposes predicting future interaction intent from multimodal context and short-term action history, then converting that intent into step-wise routing weights that dynamically balance global and local views during action generation. Because the routing module sits on the action-generation side without altering the visual encoder or language backbone, it is designed as a lightweight, plug-in upgrade for existing VLAs. It is evaluated on all 50 tasks of the RoboTwin 2.0 benchmark and on six real-world manipulation tasks, reporting 10+ percentage point improvements over a $\pi_{0.5}$ baseline trained under identical conditions.

PhysTrace evaluates physical consistency in videos by temporally aligning MLLM-generated, history-conditioned expectations with actual observations in a shared embedding space. Unlike prior work that probes internal representations or assigns video-level scores, it pinpoints when and why physical violations occur. The authors also introduce IntPhys2-Timing, adding temporal annotations to benchmark violation localization. Applied to diffusion and flow-based video models, PhysTrace reveals how physical inconsistencies emerge across generative timesteps—a crucial diagnostic as pretrained video backbones become policy priors for robot control.

Natural-language robot control requires mapping user requests to predefined tool subsets without inventing new capabilities. This paper frames tool routing as bounded multi-label selection over a fixed catalog and compares three ChromaDB retrieval policies against a cloud-hosted 120-billion-parameter LLM. The core finding is a clean quality-latency trade-off: clause-aware retrieval (CDBv3) runs locally in milliseconds but lags the LLM in routing accuracy, making it suitable for connectivity-constrained or privacy-sensitive deployments.

LAST-V2X addresses the problem of testing how delayed, missing, or corrupted V2X messages compromise safety-critical driving decisions. Its core idea is a framework that translates natural-language test descriptions into executable CARLA scenarios, then causally verifies whether any observed violations are actually due to degraded communication rather than ordinary traffic risk. This matters because existing adversarial methods perturb only the physical world, whereas V2X failures propagate from the information layer and must be isolated through paired counterfactual execution.

This paper tackles behavior cloning (BC) for autonomous driving in the CARLA simulator when only a handful of expert demonstrations are available. The core idea is to reweight the supervised BC loss by the inverse of a kernel density estimate over actions, up-weighting rare but safety-critical behaviors such as stopping at red lights and accelerating from a standstill. The motivation is that uniform BC easily ignores these low-density events in small datasets, which can lead to dangerous traffic-light violations and poor generalization.

This paper investigates whether high-performing humanoid control networks can be synthesized directly in weight space rather than trained conventionally. The authors adopt a latent diffusion framework---pairing a cluster-wise linear autoencoder with a Diffusion Transformer---to generate weights for 3-layer MLP policies on a Unitree G1 robot, achieving zero-shot sim-to-real transfer for walking, dancing, and spin kick. Alongside generation, they analyze the learned weights and identify a kinematic prior in first-layer parameters that emerges under both reinforcement and imitation learning, suggesting embodiment-specific structure in policy weights.

Mobile manipulation demands precise coordination between a mobile base and a robotic arm, making real-world policy fine-tuning difficult because of high-dimensional, tightly coupled action spaces. This paper proposes HiRe-MoMa, a framework that freezes a pre-trained base policy and learns a small, hierarchical residual: one head corrects the base motion while the other corrects the arm conditioned on the base correction. It also guides learning with sparse human teleoperation interventions via an auxiliary critic-ranking loss, reporting large success-rate gains on a TIAGo++ robot after roughly 30 minutes of online interaction.

Goal misgeneralization in RL looks uniform from the outside—agents competently pursue proxies instead of intended goals—but this paper argues it is not a single failure. By tracing goal information through networks in three Procgen games and five simulated robot tasks, the authors identify three distinct alignment failures—functional target substitution, policy shortcuts, and cue competition—and show that the depth at which the goal is lost determines which test-time repair works. The result is a principled diagnostic framework that connects internal representations to intervention strategies, moving beyond purely behavioral descriptions of misalignment.

Most robot VLAs rely on wrist cameras for manipulation detail, which narrows scene coverage and adds hardware complexity. FoveaVLA removes that dependency by teaching a π0.5-based policy to predict future interaction regions, cropping high-resolution 'foveal' patches from external stereo views to recover fine gripper-and-object detail. Post-trained on DROID with RoboInter annotations, the model achieves 77.1% overall real-world success with two external RGB-D views versus 52.1% for the wrist-equipped baseline. The idea is biologically grounded and architecturally clean, though the evaluation scale and claims about learning from human videos remain tentative.

MUCO proposes manipulation units (MUs) to decompose long-horizon robot manipulation into reusable, verifiable sub-operations. Each MU carries a local goal, an initiation condition, and observable success/failure criteria; the MUCO framework matches MUs to specialist policy executors from a frozen capability registry, enables local retry and fallback, and avoids replaying already-verified prefixes. The conceptual goal is to reduce data-collection costs, enable cross-task reuse, and contain failures without joint training or shared backbones. The critical caveat is that the submitted preprint contains almost no quantitative results.

Existing robot policies use a single fixed parameter configuration across all interaction contexts, which forces shared weights to reconcile competing adaptation signals from diverse manipulation operations. MorphAct addresses this by introducing two coupled generators that synthesize context-dependent low-rank updates for the vision-language and action modules, where the action-side generator is conditioned on the adapted visual-language representations. This allows the effective policy weights to morph at each replanning step without test-time optimization or operation labels. Evaluations across three VLA backbones ($\pi_0$, $\pi_{0.5}$, and X-VLA), two simulation benchmarks, and four real-world tasks report closed-loop success gains of up to 16.30%, accompanied by ablations isolating the value of contextual generation and cross-module coupling.

The paper tackles robust multi-agent driving policies that generalize beyond their training domain. Its core idea is UncArms, a self-play scheme where probing agents are rewarded for increasing neighbors' epistemic uncertainty ($\Delta \mathrm{Unc}$), automatically generating a hard-case curriculum without hand-crafted scenarios. This matters because prior conditioned diversity methods impose a "diversity tax" on driving performance, and this work is the first to show a conditioned policy surpassing a strong unconditional self-play baseline.

The paper tackles realistic gaze generation for a humanoid robot, separating the semantic choice of where to look from the physical motion of neck, eyes, and eyelids. Its Realistic Gaze Transformer (RGT) is a Transformer-VAE trained on retargeted human recordings and fine-tuned autoregressively to handle closed-loop rollout. Combined with an asynchronous vision-language model for target selection, the framework aims to make robot gaze more lifelike in real time. The authors benchmark kinematic fidelity but explicitly acknowledge that perceived naturalness and full pipeline accuracy are still open questions.