Daily Papers Arch&EAI

Recent advances in robotic manipulation have highlighted the effectiveness of learning from demonstration. However, while end-to-end policies excel in expressivity and flexibility, they struggle both in generalizing to novel object geometries and in attaining a high degree of precision. An alternative, object-centric approach frames the task as predicting the placement pose of the target object, providing a modular decomposition of the problem. Building on this goal-prediction paradigm, we propose TAX-DPD, a hierarchical, disentangled point diffusion framework that achieves state-of-the-art performance in placement precision, multi-modal coverage, and generalization to variations in object geometries and scene configurations. We model global scene-level placements through a novel feed-forward Dense Gaussian Mixture Model (GMM) that yields a spatially dense prior over global placements; we then model the local object-level configuration through a novel disentangled point cloud diffusion module that separately diffuses the object geometry and the placement frame, enabling precise local geometric reasoning. Interestingly, we demonstrate that our point cloud diffusion achieves substantially higher accuracy than a prior approach based on SE(3)-diffusion, even in the context of rigid object placement. We validate our approach across a suite of challenging tasks in simulation and in the real-world on high-precision industrial insertion tasks. Furthermore, we present results on a cloth-hanging task in simulation, indicating that our framework can further relax assumptions on object rigidity.

Recent advances in robotic manipulation have highlighted the effectiveness of learning from demonstration.

Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for building general-purpose robotic agents. However, the VLA landscape remains highly fragmented and complex: as existing approaches vary substantially in architectures, training data, embodiment configurations, and benchmark-specific engineering. In this work, we introduce StarVLA-$α$, a simple yet strong baseline designed to study VLA design choices under controlled conditions. StarVLA-$α$ deliberately minimizes architectural and pipeline complexity to reduce experimental confounders and enable systematic analysis. Specifically, we re-evaluate several key design axes, including action modeling strategies, robot-specific pretraining, and interface engineering. Across unified multi-benchmark training on LIBERO, SimplerEnv, RoboTwin, and RoboCasa, the same simple baseline remains highly competitive, indicating that a strong VLM backbone combined with minimal design is already sufficient to achieve strong performance without relying on additional architectural complexity or engineering tricks. Notably, our single generalist model outperforms $π_{0.5}$ by 20\% on the public real-world RoboChallenge benchmark. We expect StarVLA-$α$ to serve as a solid starting point for future research in the VLA regime. Code will be released at https://github.com/starVLA/starVLA.

Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for building general-purpose robotic agents.

In Model Predictive Control (MPC), world models predict the future outcomes of various action proposals, which are then scored to guide the selection of the optimal action. For visuomotor MPC, the score function is a distance metric between a predicted image and a goal image, measured in the latent space of a pretrained vision encoder like DINO and JEPA. However, it is challenging to obtain the goal image in advance of the task execution, particularly in new environments. Additionally, conveying the goal through an image offers limited interactivity compared with natural language. In this work, we propose to learn a Grounded World Model (GWM) in a vision-language-aligned latent space. As a result, each proposed action is scored based on how close its future outcome is to the task instruction, reflected by the similarity of embeddings. This approach transforms the visuomotor MPC to a VLA that surpasses VLM-based VLAs in semantic generalization. On the proposed WISER benchmark, GWM-MPC achieves a 87% success rate on the test set comprising 288 tasks that feature unseen visual signals and referring expressions, yet remain solvable with motions demonstrated during training. In contrast, traditional VLAs achieve an average success rate of 22%, even though they overfit the training set with a 90% success rate.

In Model Predictive Control (MPC), world models predict the future outcomes of various action proposals, which are then scored to guide the selection of the optimal action.

While the shortage of explicit action data limits Vision-Language-Action (VLA) models, human action videos offer a scalable yet unlabeled data source. A critical challenge in utilizing large-scale human video datasets lies in transforming visual signals into ontology-independent representations, known as latent actions. However, the capacity of latent action representation to derive robust control from visual observations has yet to be rigorously evaluated. We introduce the Latent Action Representation Yielding (LARY) Benchmark, a unified framework for evaluating latent action representations on both high-level semantic actions (what to do) and low-level robotic control (how to do). The comprehensively curated dataset encompasses over one million videos (1,000 hours) spanning 151 action categories, alongside 620K image pairs and 595K motion trajectories across diverse embodiments and environments. Our experiments reveal two crucial insights: (i) General visual foundation models, trained without any action supervision, consistently outperform specialized embodied latent action models. (ii) Latent-based visual space is fundamentally better aligned to physical action space than pixel-based space. These results suggest that general visual representations inherently encode action-relevant knowledge for physical control, and that semantic-level abstraction serves as a fundamentally more effective pathway from vision to action than pixel-level reconstruction.

While the shortage of explicit action data limits Vision-Language-Action (VLA) models, human action videos offer a scalable yet unlabeled data source.

Simulation-based data generation has become a dominant paradigm for training robotic manipulation policies, yet existing platforms do not incorporate object affordance information into trajectory generation. As a result, tasks requiring precise interaction with specific functional regions--grasping a mug by its handle, pouring from a cup's rim, or hanging a mug on a hook--cannot be automatically generated with semantically correct trajectories. We introduce AffordSim, the first simulation framework that integrates open-vocabulary 3D affordance prediction into the manipulation data generation pipeline. AffordSim uses our VoxAfford model, an open-vocabulary 3D affordance detector that enhances MLLM output tokens with multi-scale geometric features, to predict affordance maps on object point clouds, guiding grasp pose estimation toward task-relevant functional regions. Built on NVIDIA Isaac Sim with cross-embodiment support (Franka FR3, Panda, UR5e, Kinova), VLM-powered task generation, and novel domain randomization using DA3-based 3D Gaussian reconstruction from real photographs, AffordSim enables automated, scalable generation of affordance-aware manipulation data. We establish a benchmark of 50 tasks across 7 categories (grasping, placing, stacking, pushing/pulling, pouring, mug hanging, long-horizon composite) and evaluate 4 imitation learning baselines (BC, Diffusion Policy, ACT, Pi 0.5). Our results reveal that while grasping is largely solved (53-93% success), affordance-demanding tasks such as pouring into narrow containers (1-43%) and mug hanging (0-47%) remain significantly more challenging for current imitation learning methods, highlighting the need for affordance-aware data generation. Zero-shot sim-to-real experiments on a real Franka FR3 validate the transferability of the generated data.

Simulation-based data generation has become a dominant paradigm for training robotic manipulation policies, yet existing platforms do not incorporate object affordance information into trajectory generation.

Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, from rapid local fluctuations to slow-evolving long-range trends. However, many contemporary architectures impose rigid, fixed-scale structural priors -- such as patch-based tokenization, predefined receptive fields, or frozen backbone encoders -- which can over-regularize temporal dynamics and limit adaptability to abrupt high-magnitude events. To handle this, we introduce the Multi-scale Temporal Network (MSTN), a hybrid neural architecture grounded in an Early Temporal Aggregation principle. MSTN integrates three complementary components: (i) a multi-scale convolutional encoder that captures fine-grained local structure; (ii) a sequence modeling module that learns long-range dependencies through either recurrent or attention-based mechanisms; and (iii) a self-gated fusion stage incorporating squeeze-excitation and a single dense layer to dynamically reweight and fuse multi-scale representations. This design enables MSTN to flexibly model temporal patterns spanning milliseconds to extended horizons, while avoiding the computational burden typically associated with long-context models. Across extensive benchmarks covering imputation, long term forecasting, short term forecasting, classification, and cross-dataset generalization, MSTN achieves state-of-the-art performance, establishing new best results on 33 of 40 datasets, while remaining lightweight ($\sim$278,520 params for MSTN-BiLSTM and $\sim$950,776 $\approx$ 1M for MSTN-Transformer) and suitable for low-latency inference ($<$1 sec, often in milliseconds), resource-constrained deployment.

Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, from rapid local fluctuations to slow-evolving long-range trends.

Multimodal perception systems for robotics and embodied AI often assume reliable RGB-D sensing, but in practice, depth is frequently missing, noisy, or corrupted. We thus present GeomPrompt, a lightweight cross-modal adaptation module that synthesizes a task-driven geometric prompt from RGB alone for the fourth channel of a frozen RGB-D semantic segmentation model, without depth supervision. We further introduce GeomPrompt-Recovery, an adaptation module that compensates for degraded depth by predicting the fourth channel correction relevant for the frozen segmenter. Both modules are trained solely with downstream segmentation supervision, enabling recovery of the geometric prior useful for segmentation, rather than estimating depth signals. On SUN RGB-D, GeomPrompt improves over RGB-only inference by +6.1 mIoU on DFormer and +3.0 mIoU on GeminiFusion, while remaining competitive with strong monocular depth estimators. For degraded depth, GeomPrompt-Recovery consistently improves robustness, yielding gains up to +3.6 mIoU under severe depth corruptions. GeomPrompt is also substantially more efficient than monocular depth baselines, reaching 7.8 ms latency versus 38.3 ms and 71.9 ms. These results suggest that task-driven geometric prompting is an efficient mechanism for cross-modal compensation under missing and degraded depth inputs in RGB-D perception.

Multimodal perception systems for robotics and embodied AI often assume reliable RGB-D sensing, but in practice, depth is frequently missing, noisy, or corrupted.

Vision-Language-Action models (VLAs) have demonstrated strong potential for embodied AI, yet their deployment on resource-limited robots remains challenging due to high memory and computational demands. While Post-Training Quantization (PTQ) provides an efficient solution, directly applying PTQ to VLAs often results in severe performance degradation during sequential control. We identify temporal error accumulation as a key factor, where quantization perturbations at the vision-language-to-action interface are progressively amplified, leading to kinematic drift in executed trajectories. To address this issue, we propose Drift-Aware Post-Training Quantization (DA-PTQ), which formulates quantization as a drift-aware optimization problem over sequential decision processes. DA-PTQ consists of two components: (1) Cross-Space Representation Compensation, which mitigates structured distortions between multimodal representations and action space to improve action consistency, and (2) Motion-Driven Mixed-Precision Allocation, which assigns bit-widths by minimizing trajectory-level motion errors. Extensive experiments show that DA-PTQ significantly reduces kinematic drift and achieves comparable performance to full-precision models under low-bit settings, enabling practical deployment of VLAs on resource-limited robotic platforms.

Vision-Language-Action models (VLAs) have demonstrated strong potential for embodied AI, yet their deployment on resource-limited robots remains challenging due to high memory and computational demands.

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. With the paradigm shift toward self-evolving agentic learning, models are increasingly expected to learn from trajectories by synthesizing tools or accumulating explicit experiences. However, prevailing methods typically rely on large-scale LLMs or multi-agent frameworks, which hinder their deployment in resource-constrained environments. The inherent sparsity of outcome-based rewards also poses a substantial challenge, as agents typically receive feedback only upon completion of tasks. To address these limitations, we introduce a Tool-Memory based self-evolving agentic framework SEARL. Unlike approaches that directly utilize interaction experiences, our method constructs a structured experience memory that integrates planning with execution. This provides a novel state abstraction that facilitates generalization across analogous contexts, such as tool reuse. Consequently, agents extract explicit knowledge from historical data while leveraging inter-trajectory correlations to densify reward signals. We evaluate our framework on knowledge reasoning and mathematics tasks, demonstrating its effectiveness in achieving more practical and efficient learning.

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks.

Recent Vision-Language-Action (VLA) models have shown impressive flexibility and generalization, yet their deployment in robotic manipulation remains limited by heavy computational overhead and inference latency. In this work, we present ActDistill, a general action-guided self-derived distillation framework that transfers the action prediction capability of any existing VLA model to a lightweight counterpart. Unlike previous efficiency strategies that primarily emphasize vision-language correlations, ActDistill leverages action priors to guide knowledge transfer and model compression, achieving action-oriented efficiency for VLA models. Specifically, we employ a well-trained VLA model as the teacher and introduce a graph-structured encapsulation strategy to explicitly model the hierarchical evolution of action prediction. The student model, derived from the graph-encapsulated teacher, is further equipped with a dynamic router that adaptively selects computation paths based on action prediction demands, guided by hierarchical graph-informed supervision to ensure smooth and efficient evolution. During inference, graph-related auxiliary components are removed, allowing the student to execute only dynamically routed layers and predict high-precision actions with minimal computation and latency. Experiments on embodied benchmarks demonstrate that ActDistill achieves comparable or superior performance to full-scale VLA models while reducing computation by over 50% with up to 1.67 times speedup, thereby establishing a general paradigm toward efficient embodied intelligence.

Recent Vision-Language-Action (VLA) models have shown impressive flexibility and generalization, yet their deployment in robotic manipulation remains limited by heavy computational overhead and inference latency.

The growing demand for deploying Small Language Models (SLMs) on edge devices, including laptops, smartphones, and embedded platforms, has exposed fundamental inefficiencies in existing accelerators. While GPUs handle prefill workloads efficiently, the autoregressive decoding phase is dominated by GEMV operations that are inherently memory-bound, resulting in poor utilization and prohibitive energy costs at the edge. In this work, we present EdgeCIM, a hardware-software co-design framework that rethinks accelerator design for end-to-end decoder-only inference. At its core is a CIM macro, implemented in 65nm, coupled with a tile-based mapping strategy that balances pipeline stages, maximizing parallelism while alleviating DRAM bandwidth bottlenecks. Our simulator enables design space exploration of SLMs up to 4B parameters, identifying Pareto-optimal configurations in terms of latency and energy. Compared to an NVIDIA Orin Nano, EdgeCIM achieves up to 7.3x higher throughput and 49.59x better energy efficiency on LLaMA3.2-1B, and delivers 9.95x higher throughput than Qualcomm SA8255P on LLaMA3.2-3B. Extensive benchmarks on TinyLLaMA-1.1B, LLaMA3.2 (1B, 3B), Phi-3.5-mini-3.8B, Qwen2.5 (0.5B, 1.5B, 3B), SmolLM2-1.7B, SmolLM3-3B, and Qwen3 (0.6B, 1.7B, 4B) reveal that our accelerator, under INT4 precision, achieves on average 336.42 tokens/s and 173.02 tokens/J. These results establish EdgeCIM as a compelling solution towards real-time, energy-efficient edge-scale SLM inference.

The growing demand for deploying Small Language Models (SLMs) on edge devices, including laptops, smartphones, and embedded platforms, has exposed fundamental inefficiencies in existing accelerators.

Dexterous robotic manipulation requires more than geometrically valid grasps: it demands physically grounded contact strategies that account for the spatially non-uniform mechanical properties of the object. However, existing grasp planners typically treat the surface as structurally homogeneous, even though contact in a weak region can damage the object despite a geometrically perfect grasp. We present a pipeline for grasp selection and force regulation in a five-fingered robotic hand, based on a map of locally admissible contact loads. From an operator command, the system identifies the target object, reconstructs its 3D geometry using SAM3D, and imports the model into Isaac Sim. A physics-informed geometric analysis then computes a force map that encodes the maximum lateral contact force admissible at each surface location without deformation. Grasp candidates are filtered by geometric validity and task-goal consistency. When multiple candidates are comparable under classical metrics, they are re-ranked using a force-map-aware criterion that favors grasps with contacts in mechanically admissible regions. An impedance controller scales the stiffness of each finger according to the locally admissible force at the contact point, enabling safe and reliable grasp execution. Validation on paper, plastic, and glass cups shows that the proposed approach consistently selects structurally stronger contact regions and keeps grip forces within safe bounds. In this way, the work reframes dexterous manipulation from a purely geometric problem into a physically grounded joint planning problem of grasp selection and grip execution for future humanoid systems.

Dexterous robotic manipulation requires more than geometrically valid grasps: it demands physically grounded contact strategies that account for the spatially non-uniform mechanical properties of the object.

Robot grasping of desktop object is widely used in intelligent manufacturing, logistics, and agriculture.Although vision-language models (VLMs) show strong potential for robotic manipulation, their deployment in low-level grasping faces key challenges: scarce high-quality multimodal demonstrations, spatial hallucination caused by weak geometric grounding, and the fragility of open-loop execution in dynamic environments. To address these challenges, we propose Closed-Loop Asynchronous Spatial Perception(CLASP), a novel asynchronous closed-loop framework that integrates multimodal perception, logical reasoning, and state-reflective feedback. First, we design a Dual-Pathway Hierarchical Perception module that decouples high-level semantic intent from geometric grounding. The design guides the output of the inference model and the definite action tuples, reducing spatial illusions. Second, an Asynchronous Closed-Loop Evaluator is implemented to compare pre- and post-execution states, providing text-based diagnostic feedback to establish a robust error-correction loop and improving the vulnerability of traditional open-loop execution in dynamic environments. Finally, we design a scalable multi-modal data engine that automatically synthesizes high-quality spatial annotations and reasoning templates from real and synthetic scenes without human teleoperation. Extensive experiments demonstrate that our approach significantly outperforms existing baselines, achieving an 87.0% overall success rate. Notably, the proposed framework exhibits remarkable generalization across diverse objects, bridging the sim-to-real gap and providing exceptional robustness in geometrically challenging categories and cluttered scenarios.

Robot grasping of desktop object is widely used in intelligent manufacturing, logistics, and agriculture.Although vision-language models (VLMs) show strong potential for robotic manipulation, their deployment in low-level grasping faces key challenges: scarce high-quality multimodal demonstrations, spatial hallucination caused by weak geometric grounding, and the fragility of open-loop execution in dynamic environments.

We present 3D-Anchored Lookahead Planning (3D-ALP), a System 2 reasoning engine for robotic manipulation that combines Monte Carlo Tree Search (MCTS) with a 3D-consistent world model as the rollout oracle. Unlike reactive policies that evaluate actions from the current camera frame only, 3D-ALP maintains a persistent camera-to-world (c2w) anchor that survives occlusion, enabling accurate replanning to object positions that are no longer directly observable. On a 5-step sequential reach task requiring spatial memory (Experiment E3), 3D-ALP achieves 0.650 0.109 success rate on memory-required steps versus 0.006 0.008 for a greedy reactive baseline (Δ=+0.645), while step 5 success reaches 0.822 against 0.000 for greedy. An ablation study (30 episodes, 3 seeds) isolates tree search spatial memory as the primary driver (+0.533, 82% of gain) with additional benefit from deeper lookahead (+0.111, 17%). We also identify and resolve four structural failure modes in applying UCT-MCTS (Upper Confidence Bounds applied to Trees [10]) to continuous robotic manipulation.

We present 3D-Anchored Lookahead Planning (3D-ALP), a System 2 reasoning engine for robotic manipulation that combines Monte Carlo Tree Search (MCTS) with a 3D-consistent world model as the rollout oracle.

Autonomous highway driving involves high-speed safety risks due to limited reaction time, where rare but dangerous events may lead to severe consequences. This places stringent requirements on trajectory planning in terms of both reliability and computational efficiency. This paper proposes a hybrid highway trajectory planning (H-HTP) framework that integrates learning-based adaptability with optimization-based formal safety guarantees. The key design principle is a deliberate division of labor: a learning module generates a traffic-adaptive velocity profile, while all safety-critical decisions including collision avoidance and kinematic feasibility are delegated to a Mixed-Integer Quadratic Program (MIQP). This design ensures that formal safety constraints are always enforced, regardless of the complexity of multi-vehicle interactions. A linearization strategy for the vehicle geometry substantially reduces the number of integer variables, enabling real-time optimization without sacrificing formal safety guarantees. Experiments on the HighD dataset demonstrate that H-HTP achieves a scenario success rate above 97% with an average planning-cycle time of approximately 54 ms, reliably producing smooth, kinematically feasible, and collision-free trajectories in safety-critical highway scenarios.

Autonomous highway driving involves high-speed safety risks due to limited reaction time, where rare but dangerous events may lead to severe consequences.

Recent progress in embodied AI has produced a growing ecosystem of robot policies, foundation models, and modular runtimes. However, current evaluation remains dominated by task success metrics such as completion rate or manipulation accuracy. These metrics leave a critical gap: they do not measure whether embodied systems are governable -- whether they respect capability boundaries, enforce policies, recover safely, maintain audit trails, and respond to human oversight. We present EmbodiedGovBench, a benchmark for governance-oriented evaluation of embodied agent systems. Rather than asking only whether a robot can complete a task, EmbodiedGovBench evaluates whether the system remains controllable, policy-bounded, recoverable, auditable, and evolution-safe under realistic perturbations. The benchmark covers seven governance dimensions: unauthorized capability invocation, runtime drift robustness, recovery success, policy portability, version upgrade safety, human override responsiveness, and audit completeness. We define a benchmark structure spanning single-robot and fleet settings, with scenario templates, perturbation operators, governance metrics, and baseline evaluation protocols. We describe how the benchmark can be instantiated over embodied capability runtimes with modular interfaces and contract-aware upgrade workflows. Our analysis suggests that embodied governance should become a first-class evaluation target. EmbodiedGovBench provides the initial measurement framework for that shift.

Recent progress in embodied AI has produced a growing ecosystem of robot policies, foundation models, and modular runtimes.

The rise of generative AI workloads, particularly language model inference, is intensifying on/off-chip memory pressure. Multimodal inputs such as video streams or images and downstream applications like Question Answering (QA) and analysis over large documents incur long context lengths, requiring caching of massive Key and Value states of the previous tokens. Even a low degree of concurrent inference serving on resource-constrained devices, like mobiles, can further add to memory capacity pressure and runtime memory management complexity. In this paper, we evaluate the performance implications of two emerging technology solutions to alleviate the memory pressure in terms of both capacity and bandwidth using a hierarchical roofline-based analytical performance model. For large models (e.g., 13B parameters) and context lengths, we investigate the performance implications of High Bandwidth Storage (HBS) and outline bandwidth/latency requirements to achieve an acceptable throughput for interactivity. For small models (e.g., 1B parameters), we evaluate the merit of a bonded global buffer memory chiplet and propose how to best utilize it.

The rise of generative AI workloads, particularly language model inference, is intensifying on/off-chip memory pressure.

Flow Matching (FM) policies have emerged as an efficient backbone for robotic control, offering fast and expressive action generation that underpins recent large-scale embodied AI systems. However, FM policies trained via imitation learning inherit the limitations of demonstration data; surpassing suboptimal behaviors requires reinforcement learning (RL) fine-tuning. Recent methods convert deterministic flows into stochastic differential equations (SDEs) with learnable noise injection, enabling exploration and tractable likelihoods, but such noise-only control can compromise training efficiency when demonstrations already provide strong priors. We observe that modulating the drift via the score function, i.e., the gradient of log-density, steers exploration toward high-probability regions, improving stability. The score admits a closed-form expression from the velocity field, requiring no auxiliary networks. Based on this, we propose ScoRe-Flow, a score-based RL fine-tuning method that combines drift modulation with learned variance prediction to achieve decoupled control over the mean and variance of stochastic transitions. Experiments demonstrate that ScoRe-Flow achieves 2.4x faster convergence than flow-based SOTA on D4RL locomotion tasks and up to 5.4% higher success rates on Robomimic and Franka Kitchen manipulation tasks.

Flow Matching (FM) policies have emerged as an efficient backbone for robotic control, offering fast and expressive action generation that underpins recent large-scale embodied AI systems.

Vision-Language-Action (VLA) models typically map visual observations and linguistic instructions directly to robotic control signals. This "black-box" mapping forces a single forward pass to simultaneously handle instruction interpretation, spatial grounding, and low-level control, often leading to poor spatial precision and limited robustness in out-of-distribution scenarios. To address these limitations, we propose VP-VLA, a dual-system framework that decouples high-level reasoning and low-level execution via a structured visual prompting interface. Specifically, a "System 2 Planner" decomposes complex instructions into sub-tasks and identifies relevant target objects and goal locations. These spatial anchors are then overlaid directly onto visual observations as structured visual prompts, such as crosshairs and bounding boxes. Guided by these prompts and enhanced by a novel auxiliary visual grounding objective during training, a "System 1 Controller" reliably generates precise low-level execution motions. Experiments on the Robocasa-GR1-Tabletop benchmark and SimplerEnv simulation demonstrate that VP-VLA improves success rates by 5% and 8.3%, surpassing competitive baselines including QwenOFT and GR00T-N1.6. Project page: https://visualprompt-vla.github.io/

Vision-Language-Action (VLA) models typically map visual observations and linguistic instructions directly to robotic control signals.

Dexterous manipulation is limited by both control and design, without consensus as to what makes manipulators best for performing dexterous tasks. This raises a fundamental challenge: how should we design and control robot manipulators that are optimized for dexterity? We present a co-design framework that learns task-specific hand morphology and complementary dexterous control policies. The framework supports 1) an expansive morphology search space including joint, finger, and palm generation, 2) scalable evaluation across the wide design space via morphology-conditioned cross-embodied control, and 3) real-world fabrication with accessible components. We evaluate the approach across multiple dexterous tasks, including in-hand rotation with simulation and real deployment. Our framework enables an end-to-end pipeline that can design, train, fabricate, and deploy a new robotic hand in under 24 hours. The full framework will be open-sourced and available on our website: https://an-axolotl.github.io/HouseofDextra/ .

Dexterous manipulation is limited by both control and design, without consensus as to what makes manipulators best for performing dexterous tasks.

Multimodal LLMs are increasingly deployed as perceptual backbones for autonomous agents in 3D environments, from robotics to virtual worlds. These applications require agents to perceive rapid state changes, attribute actions to the correct entities, and reason about concurrent multi-agent behaviors from a first-person perspective, capabilities that existing benchmarks do not adequately evaluate. We introduce GameplayQA, a framework for evaluating agentic-centric perception and reasoning through video understanding. Specifically, we densely annotate multiplayer 3D gameplay videos at 1.22 labels/second, with time-synced, concurrent captions of states, actions, and events structured around a triadic system of Self, Other Agents, and the World, a natural decomposition for multi-agent environments. From these annotations, we refined 2.4K diagnostic QA pairs organized into three levels of cognitive complexity, accompanied by a structured distractor taxonomy that enables fine-grained analysis of where models hallucinate. Evaluation of frontier MLLMs reveals a substantial gap from human performance, with common failures in temporal and cross-video grounding, agent-role attribution, and handling the decision density of the game. We hope GameplayQA stimulates future research at the intersection of embodied AI, agentic perception, and world modeling.

Multimodal LLMs are increasingly deployed as perceptual backbones for autonomous agents in 3D environments, from robotics to virtual worlds.

Ensemble methods are widely used to improve predictive performance, but their effectiveness often comes at the cost of increased memory usage and computational complexity. In this paper, we identify a conflict in aggregation strategies that negatively impacts prediction stability. We propose test-time adaptation (StableTTA), a training-free method employs novel image and logit processing. Empirical results on ImageNet-1K show gains of 10.93\%-32.82\% in top-1 accuracy, with 33 models achieving over 95\% accuracy and several surpassing 96\%. Notably, StableTTA allows lightweight architectures to outperform ViT by 11.75\% in top-1 accuracy while reducing parameter count and computational cost by 97.1\% and 89.1\%, respectively, enabling high-accuracy inference on resource-constrained devices. Code is available at: https://github.com/LizhengMathAi/StableTTA, including a 3-minute reproduction demo.

Ensemble methods are widely used to improve predictive performance, but their effectiveness often comes at the cost of increased memory usage and computational complexity.

A fundamental challenge in embodied intelligence is developing expressive and compact state representations for efficient world modeling and decision making. However, existing methods often fail to achieve this balance, yielding representations that are either overly redundant or lacking in task-critical information. We propose an unsupervised approach that learns a highly compressed two-token state representation using a lightweight encoder and a pre-trained Diffusion Transformer (DiT) decoder, capitalizing on its strong generative prior. Our representation is efficient, interpretable, and integrates seamlessly into existing VLA-based models, improving performance by 14.3% on LIBERO and 30% in real-world task success with minimal inference overhead. More importantly, we find that the difference between these tokens, obtained via latent interpolation, naturally serves as a highly effective latent action, which can be further decoded into executable robot actions. This emergent capability reveals that our representation captures structured dynamics without explicit supervision. We name our method StaMo for its ability to learn generalizable robotic Motion from compact State representation, which is encoded from static images, challenging the prevalent dependence to learning latent action on complex architectures and video data. The resulting latent actions also enhance policy co-training, outperforming prior methods by 10.4% with improved interpretability. Moreover, our approach scales effectively across diverse data sources, including real-world robot data, simulation, and human egocentric video.

A fundamental challenge in embodied intelligence is developing expressive and compact state representations for efficient world modeling and decision making.

Human-in-the-loop (HITL) UAV operation is essential in complex and safety-critical aerial surveying environments, where human operators provide navigation intent while onboard autonomy must maintain accurate and robust state estimation. A key challenge in this setting is that resource-constrained UAV platforms are often limited to narrow-field-of-view LiDAR sensors. In geometrically degenerate or feature-sparse scenes, limited sensing coverage often weakens LiDAR Inertial Odometry (LIO)'s observability, causing drift accumulation, degraded geometric accuracy, and unstable state estimation, which directly compromise safe and effective HITL operation and the reliability of downstream surveying products. To overcome this limitation, we present AWARE, a bio-inspired whole-body active yawing framework that exploits the UAV's own rotational agility to extend the effective sensor horizon and improve LIO's observability without additional mechanical actuation. The core of AWARE is a differentiable Model Predictive Control (MPC) framework embedded in a Reinforcement Learning (RL) loop. It first identifies the viewing direction that maximizes information gain across the full yaw space, and a lightweight RL agent then adjusts the MPC cost weights online according to the current environmental context, enabling an adaptive balance between estimation accuracy and flight stability. A Safe Flight Corridor mechanism further ensures operational safety within this HITL paradigm by decoupling the operator's navigational intent from autonomous yaw optimization to enable safe and efficient cooperative control. We validate AWARE through extensive experiments in diverse simulated and real-world environments.

Human-in-the-loop (HITL) UAV operation is essential in complex and safety-critical aerial surveying environments, where human operators provide navigation intent while onboard autonomy must maintain accurate and robust state estimation.

Visual Language Navigation (VLN) is one of the fundamental capabilities for embodied intelligence and a critical challenge that urgently needs to be addressed. However, existing methods are still unsatisfactory in terms of both success rate (SR) and generalization: Supervised Fine-Tuning (SFT) approaches typically achieve higher SR, while Training-Free (TF) approaches often generalize better, but it is difficult to obtain both simultaneously. To this end, we propose a Memory-Execute-Review framework. It consists of three parts: a hierarchical memory module for providing information support, an execute module for routine decision-making and actions, and a review module for handling abnormal situations and correcting behavior. We validated the effectiveness of this framework on the Object Goal Navigation task. Across 4 datasets, our average SR achieved absolute improvements of 7% and 5% compared to all baseline methods under TF and Zero-Shot (ZS) settings, respectively. On the most commonly used HM3D_v0.1 and the more challenging open vocabulary dataset HM3D_OVON, the SR improved by 8% and 6%, under ZS settings. Furthermore, on the MP3D and HM3D_OVON datasets, our method not only outperformed all TF methods but also surpassed all SFT methods, achieving comprehensive leadership in both SR (5% and 2%) and generalization. Additionally, we deployed the MerNav model on the humanoid robot and conducted experiments in the real world. The project address is: https://qidekang.github.io/MerNav.github.io/

Visual Language Navigation (VLN) is one of the fundamental capabilities for embodied intelligence and a critical challenge that urgently needs to be addressed.

Despite the recent success of modern imitation learning methods in robot manipulation, their performance is often constrained by geometric variations due to limited data diversity. Leveraging powerful 3D generative models and vision foundation models (VFMs), the proposed AffordGen framework overcomes this limitation by utilizing the semantic correspondence of meaningful keypoints across large-scale 3D meshes to generate new robot manipulation trajectories. This large-scale, affordance-aware dataset is then used to train a robust, closed-loop visuomotor policy, combining the semantic generalizability of affordances with the reactive robustness of end-to-end learning. Experiments in simulation and the real world show that policies trained with AffordGen achieve high success rates and enable zero-shot generalization to truly unseen objects, significantly improving data efficiency in robot learning.

Despite the recent success of modern imitation learning methods in robot manipulation, their performance is often constrained by geometric variations due to limited data diversity.

LLMs now form the backbone of AI agents across a diverse range of applications, including tool use, command-line interfaces, and web or computer interaction. These agentic LLM inference tasks are fundamentally different from chatbot-focused inference. They often involve much longer context lengths to capture complex and prolonged inputs, such as an entire webpage DOM or complicated tool-call trajectories. This, in turn, generates significant off-chip memory traffic during inference and causes workloads to be constrained by two memory walls, namely the bandwidth wall and the capacity wall, preventing compute units from achieving high utilization. In this paper, we introduce PLENA, a hardware-software co-designed system built around three core optimization pathways. PLENA features a novel flattened systolic-array architecture (Pathway 1) and efficient compute and memory units that support an asymmetric quantization scheme (Pathway 2). It also provides native support for FlashAttention (Pathway 3). In addition, PLENA includes a complete software-hardware stack, consisting of a custom ISA, a compiler, a transaction-level simulator, and an automated design-space exploration flow. Experimental results show that PLENA delivers up to 2.23x and 4.70x higher throughput than the A100 GPU and TPU v6e, respectively, under identical multiplier counts and memory configurations during LLaMA agentic inference. PLENA also achieves up to 4.04x higher energy efficiency than the A100 GPU. The full PLENA system, including its simulator, compiler, ISA, and RTL implementation, will be open-sourced to the research community.

LLMs now form the backbone of AI agents across a diverse range of applications, including tool use, command-line interfaces, and web or computer interaction.

Key-Value (KV) cache plays a crucial role in accelerating inference in large language models (LLMs) by storing intermediate attention states and avoiding redundant computation during autoregressive generation. However, its memory footprint scales linearly with sequence length, often leading to severe memory bottlenecks on resource-constrained hardware. Prior work has explored offloading KV cache to the CPU while retaining only a subset on the GPU, but these approaches often rely on imprecise token selection and suffer performance degradation in long-generation tasks such as chain-of-thought reasoning. In this paper, we propose a novel KV cache management strategy, IceCache, which integrates semantic token clustering with PagedAttention. By organizing semantically related tokens into contiguous memory regions managed by a hierarchical, dynamically updatable data structure, our method enables more efficient token selection and better utilization of memory bandwidth during CPU-GPU transfers. Experimental results on LongBench show that, with a 256-token budget, IceCache maintains 99% of the original accuracy achieved by the full KV cache model. Moreover, compared to other offloading-based methods, IceCache attains competitive or even superior latency and accuracy while using only 25% of the KV cache token budget, demonstrating its effectiveness in long-sequence scenarios. The code is available on our project website at https://yuzhenmao.github.io/IceCache/.

Key-Value (KV) cache plays a crucial role in accelerating inference in large language models (LLMs) by storing intermediate attention states and avoiding redundant computation during autoregressive generation.

Conventional Vision-and-Language Navigation (VLN) benchmarks assume instructions are feasible and the referenced target exists, leaving agents ill-equipped to handle false-premise goals. We introduce VLN-NF, a benchmark with false-premise instructions where the target is absent from the specified room and agents must navigate, gather evidence through in-room exploration, and explicitly output NOT-FOUND. VLN-NF is constructed via a scalable pipeline that rewrites VLN instructions using an LLM and verifies target absence with a VLM, producing plausible yet factually incorrect goals. We further propose REV-SPL to jointly evaluate room reaching, exploration coverage, and decision correctness. To address this challenge, we present ROAM, a two-stage hybrid that combines supervised room-level navigation with LLM/VLM-driven in-room exploration guided by a free-space clearance prior. ROAM achieves the best REV-SPL among compared methods, while baselines often under-explore and terminate prematurely under unreliable instructions. VLN-NF project page can be found at https://vln-nf.github.io/.

Conventional Vision-and-Language Navigation (VLN) benchmarks assume instructions are feasible and the referenced target exists, leaving agents ill-equipped to handle false-premise goals.

Asynchronous inference has emerged as a prevalent paradigm in robotic manipulation, achieving significant progress in ensuring trajectory smoothness and efficiency. However, a systemic challenge remains unresolved, as inherent latency causes generated actions to inevitably lag behind the real-time environment. This issue is particularly exacerbated in dynamic scenarios, where such temporal misalignment severely compromises the policy's ability to interpret and react to rapidly evolving surroundings. In this paper, we propose a novel framework that leverages predicted object flow to synthesize future observations, incorporating a flow-based contrastive learning objective to align the visual feature representations of predicted observations with ground-truth future states. Empowered by this anticipated visual context, our asynchronous policy gains the capacity for proactive planning and motion, enabling it to explicitly compensate for latency and robustly execute manipulation tasks involving actively moving objects. Experimental results demonstrate that our approach significantly enhances responsiveness and success rates in complex dynamic manipulation tasks.

Asynchronous inference has emerged as a prevalent paradigm in robotic manipulation, achieving significant progress in ensuring trajectory smoothness and efficiency.