Daily Papers Arch&EAI

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.

Chain-of-Thought (CoT) reasoning has become a powerful driver of trajectory prediction in VLA-based autonomous driving, yet its autoregressive nature imposes a latency cost that is prohibitive for real-time deployment. Latent CoT methods attempt to close this gap by compressing reasoning into continuous hidden states, but consistently fall short of their explicit counterparts. We suggest that this is due to purely linguistic latent representations compressing a symbolic abstraction of the world, rather than the causal dynamics that actually govern driving. Thus, we present OneVL (One-step latent reasoning and planning with Vision-Language explanations), a unified VLA and World Model framework that routes reasoning through compact latent tokens supervised by dual auxiliary decoders. Alongside a language decoder that reconstructs text CoT, we introduce a visual world model decoder that predicts future-frame tokens, forcing the latent space to internalize the causal dynamics of road geometry, agent motion, and environmental change. A three-stage training pipeline progressively aligns these latents with trajectory, language, and visual objectives, ensuring stable joint optimization. At inference, the auxiliary decoders are discarded and all latent tokens are prefilled in a single parallel pass, matching the speed of answer-only prediction. Across four benchmarks, OneVL becomes the first latent CoT method to surpass explicit CoT, delivering state-of-the-art accuracy at answer-only latency, and providing direct evidence that tighter compression, when guided in both language and world-model supervision, produces more generalizable representations than verbose token-by-token reasoning. Project Page: https://xiaomi-embodied-intelligence.github.io/OneVL

Chain-of-Thought (CoT) reasoning has become a powerful driver of trajectory prediction in VLA-based autonomous driving, yet its autoregressive nature imposes a latency cost that is prohibitive for real-time deployment.

Vision-Language-Action (VLA) models drive next-generation autonomous systems, but training them requires scalable, high-quality annotations from complex environments. Current cloud pipelines rely on generic vision-language models (VLMs) that lack geometric reasoning and domain semantics due to their 2D image-text pretraining. To address this mismatch, we propose XEmbodied, a cloud-side foundation model that endows VLMs with intrinsic 3D geometric awareness and interaction with physical cues (e.g., occupancy grids, 3D boxes). Instead of treating geometry as auxiliary input, XEmbodied integrates geometric representations via a structured 3D Adapter and distills physical signals into context tokens using an Efficient Image-Embodied Adapter. Through progressive domain curriculum and reinforcement learning post-training, XEmbodied preserves general capabilities while demonstrating robust performance across 18 public benchmarks. It significantly improves spatial reasoning, traffic semantics, embodied affordance, and out-of-distribution generalization for large-scale scenario mining and embodied VQA.

Vision-Language-Action (VLA) models drive next-generation autonomous systems, but training them requires scalable, high-quality annotations from complex environments.

It introduces FractalNet, a fractal-inspired computational architectures for advanced large language model analysis that mainly challenges model diversity on a large scale in an efficient manner. The new set-up involves a template-driven generator, runner, and evaluation framework that, through systematic permutations of convolutional, normalization, activation, and dropout layers, can create more than 1,200 variants of neural networks. Fractal templates allow for structural recursion and multi-column pathways, thus, models become deeper and wider in a balanced way. Training utilizes PyTorch, Automatic Mixed Precision (AMP), and gradient checkpointing and is carried out on the CIFAR-10 dataset for five epochs. The outcomes show that fractal-based architectures are capable of strong performance and are computationally efficient. The paper positions fractal design as a feasible and resource-efficient method of automated architecture exploration.

It introduces FractalNet, a fractal-inspired computational architectures for advanced large language model analysis that mainly challenges model diversity on a large scale in an efficient manner.

Vision-Language-Action (VLA) models have demonstrated impressive capabilities in generalized robotic control; however, they remain notoriously brittle to linguistic perturbations. We identify a critical ``modality collapse'' phenomenon where strong visual priors overwhelm sparse linguistic signals, causing agents to overfit to specific instruction phrasings while ignoring the underlying semantic intent. To address this, we propose Residual Semantic Steering (RSS), a probabilistic framework that disentangles physical affordance from semantic execution. RSS introduces two theoretical innovations: (1) Monte Carlo Syntactic Integration, which approximates the true semantic posterior via dense, LLM-driven distributional expansion, and (2) Residual Affordance Steering, a dual-stream decoding mechanism that explicitly isolates the causal influence of language by subtracting the visual affordance prior. Theoretical analysis suggests that RSS effectively maximizes the mutual information between action and intent while suppressing visual distractors. Empirical results across diverse manipulation benchmarks demonstrate that RSS achieves state-of-the-art robustness, maintaining performance even under adversarial linguistic perturbations. We release our code at https://github.com/Doo-mon/RSS.

Vision-Language-Action (VLA) models have demonstrated impressive capabilities in generalized robotic control; however, they remain notoriously brittle to linguistic perturbations.

The advancement of Embodied AI heavily relies on large-scale, simulatable 3D scene datasets characterized by scene diversity and realistic layouts. However, existing datasets typically suffer from limitations in data scale or diversity, sanitized layouts lacking small items, and severe object collisions. To address these shortcomings, we introduce \textbf{InternScenes}, a novel large-scale simulatable indoor scene dataset comprising approximately 40,000 diverse scenes by integrating three disparate scene sources, real-world scans, procedurally generated scenes, and designer-created scenes, including 1.96M 3D objects and covering 15 common scene types and 288 object classes. We particularly preserve massive small items in the scenes, resulting in realistic and complex layouts with an average of 41.5 objects per region. Our comprehensive data processing pipeline ensures simulatability by creating real-to-sim replicas for real-world scans, enhances interactivity by incorporating interactive objects into these scenes, and resolves object collisions by physical simulations. We demonstrate the value of InternScenes with two benchmark applications: scene layout generation and point-goal navigation. Both show the new challenges posed by the complex and realistic layouts. More importantly, InternScenes paves the way for scaling up the model training for both tasks, making the generation and navigation in such complex scenes possible. We commit to open-sourcing the data, models, and benchmarks to benefit the whole community.

The advancement of Embodied AI heavily relies on large-scale, simulatable 3D scene datasets characterized by scene diversity and realistic layouts.

Signal Temporal Logic (STL) is a powerful language for specifying temporally structured robotic tasks. Planning executable trajectories under STL constraints remains difficult when system dynamics and environment structure are not analytically available. Existing methods typically either assume explicit models or learn task-specific behaviors, limiting zero-shot generalization to unseen STL tasks. In this work, we study offline STL planning under unknown dynamics using only task-agnostic trajectory data. Our central design philosophy is to separate logical reasoning from trajectory realization. We instantiate this idea in DAG-STL, a hierarchical framework that converts long-horizon STL planning into three stages. It first decomposes an STL formula into reachability and invariance progress conditions linked by shared timing constraints. It then allocates timed waypoints using learned reachability-time estimates. Finally, it synthesizes trajectories between these waypoints with a diffusion-based generator. This decomposition--allocation--generation pipeline reduces global planning to shorter, better-supported subproblems. To bridge the gap between planning-level correctness and execution-level feasibility, we further introduce a rollout-free dynamic consistency metric, an anytime refinement search procedure for improving multiple allocation hypotheses under finite budgets, and a hierarchical online replanning mechanism for execution-time recovery. Experiments in Maze2D, OGBench AntMaze, and the Cube domain show that DAG-STL substantially outperforms direct robustness-guided diffusion on complex long-horizon STL tasks and generalizes across navigation and manipulation settings. In a custom environment with an optimization-based reference, DAG-STL recovers most model-solvable tasks while retaining a clear computational advantage over direct optimization based on the explicit system model.

Signal Temporal Logic (STL) is a powerful language for specifying temporally structured robotic tasks.

Privacy represents one of the most critical yet underaddressed barriers to AI adoption in mental healthcare -- particularly in high-sensitivity operational environments such as military, correctional, and remote healthcare settings, where the risk of patient data exposure can deter help-seeking behavior entirely. Existing AI-enabled psychiatric decision support systems predominantly rely on cloud-based inference pipelines, requiring sensitive patient data to leave the device and traverse external servers, creating unacceptable privacy and security risks in these contexts. In this paper, we propose a zero-egress, on-device AI platform for privacy-preserving psychiatric decision support, deployed as a cross-platform mobile application. The proposed system extends our prior work on fine-tuned LLM consortiums for psychiatric diagnosis standardization by fundamentally re-architecting the inference pipeline for fully local execution -- ensuring that no patient data is transmitted to, processed by, or stored on any external server at any stage. The platform integrates a consortium of three lightweight, fine-tuned, and quantized open-source LLMs -- Gemma, Phi-3.5-mini, and Qwen2 -- selected for their compact architectures and proven efficiency on resource-constrained mobile hardware. An on-device orchestration layer coordinates ensemble inference and consensus-based diagnostic reasoning, producing DSM-5-aligned assessments for conditions. The platform is designed to assist clinicians with differential diagnosis and evidence-linked symptom mapping, as well as to support patient-facing self-screening with appropriate clinical safeguards. Initial evaluation demonstrates that the proposed zero-egress deployment achieves diagnostic accuracy comparable to its server-side predecessor while sustaining real-time inference latency on commodity mobile hardware.

Privacy represents one of the most critical yet underaddressed barriers to AI adoption in mental healthcare -- particularly in high-sensitivity operational environments such as military, correctional, and remote healthcare settings, where the risk of patient data exposure can deter help-seeking behavior entirely.

Efficient structural perception is essential for mapping and autonomous navigation on resource-constrained robots. Existing 3D methods are computationally prohibitive, while traditional 2D geometric approaches lack robustness. This paper presents a lightweight, real-time framework that projects 3D LiDAR data into 2D Bird's-Eye-View (BEV) images to enable efficient detection of structural elements relevant to mapping and navigation. Within this representation, we systematically evaluate several feature extraction strategies, including classical geometric techniques (Hough Transform, RANSAC, and LSD) and a deep learning detector based on YOLO-OBB. The resulting detections are integrated through a spatiotemporal fusion module that improves stability and robustness across consecutive frames. Experiments conducted on a standard mobile robotic platform highlight clear performance trade-offs. Classical methods such as Hough and LSD provide fast responses but exhibit strong sensitivity to noise, with LSD producing excessive segment fragmentation that leads to system congestion. RANSAC offers improved robustness but fails to meet real-time constraints. In contrast, the YOLO-OBB-based approach achieves the best balance between robustness and computational efficiency, maintaining an end-to-end latency (satisfying 10 Hz operation) while effectively filtering cluttered observations in a low-power single-board computer (SBC) without using GPU acceleration. The main contribution of this work is a computationally efficient BEV-based perception pipeline enabling reliable real-time structural detection from 3D LiDAR on resource-constrained robotic platforms that cannot rely on GPU-intensive processing. The source code and pre-trained models are publicly available.

Efficient structural perception is essential for mapping and autonomous navigation on resource-constrained robots.

Does Chain-of-Thought (CoT) reasoning genuinely improve Vision-Language-Action (VLA) models, or does it merely add overhead? Existing CoT-VLA systems report limited and inconsistent gains, yet no prior work has rigorously diagnosed when and why CoT helps robots act. Through systematic experiments, we identify two necessary conditions that must be jointly satisfied for CoT to be effective in VLA: (1) Decoding Alignment -- CoT and actions must be generated with modality-appropriate mechanisms; forcing both through a single autoregressive decoder is not merely suboptimal but actively harmful, degrading performance by 4.2 percentage points; (2) Causal Alignment -- CoT must be causally linked to task success via outcome-based optimization; without it, supervised CoT is indistinguishable from no reasoning at all under distribution shift, exhibiting a 32.0\,pp performance drop nearly identical to the 31.6\,pp drop of a reasoning-free baseline. Guided by these findings, we build DeepThinkVLA: a hybrid-attention decoder satisfies Condition~1 by pairing causal attention for language with bidirectional attention for parallel action decoding, while a two-stage SFT-then-RL pipeline satisfies Condition~2 by aligning the full reasoning--action chain with sparse task-success rewards. DeepThinkVLA achieves 97.0\% success on LIBERO, 79.0\% robustness on LIBERO-Plus (vs.\ 61.6\% for $π_0$-FAST), and 59.3\% success on RoboTwin~2.0, exceeding the strongest baseline by 21.7 points. Furthermore, we validate the practical effectiveness of our approach through real-world robot experiments. Code available at https://github.com/OpenBMB/DeepThinkVLA

Does Chain-of-Thought (CoT) reasoning genuinely improve Vision-Language-Action (VLA) models, or does it merely add overhead?

We present VoodooNet, a non-iterative neural architecture that replaces the stochastic gradient descent (SGD) paradigm with a closed-form analytic solution via Galactic Expansion. By projecting input manifolds into a high-dimensional, high-entropy "Galactic" space ($d \gg 784$), we demonstrate that complex features can be untangled without the thermodynamic cost of backpropagation. Utilizing the Moore-Penrose pseudoinverse to solve for the output layer in a single step, VoodooNet achieves a classification accuracy of \textbf{98.10\% on MNIST} and \textbf{86.63\% on Fashion-MNIST}. Notably, our results on Fashion-MNIST surpass a 10-epoch SGD baseline (84.41\%) while reducing the training time by orders of magnitude. We observe a near-logarithmic scaling law between dimensionality and accuracy, suggesting that performance is a function of "Galactic" volume rather than iterative refinement. This "Magic Hat" approach offers a new frontier for real-time Edge AI, where the traditional training phase is bypassed in favor of instantaneous manifold discovery.

We present VoodooNet, a non-iterative neural architecture that replaces the stochastic gradient descent (SGD) paradigm with a closed-form analytic solution via Galactic Expansion.

Deploying learned robot manipulation policies in industrial settings requires rigorous pre-deployment validation, yet exhaustive testing across high-dimensional parameter spaces is intractable. We present ROBOGATE, a deployment risk management framework that combines physics-based simulation with a two-stage adaptive sampling strategy to efficiently discover failure boundaries in the operational parameter space. Stage 1 employs Latin Hypercube Sampling (LHS) across an 8-dimensional parameter space; Stage 2 applies boundary-focused sampling concentrated in the 30-70% success rate transition zone. Using NVIDIA Isaac Sim with Newton physics, we evaluate a scripted pick-and-place controller across four robot embodiments -- Franka Panda (7-DOF), UR3e (6-DOF), UR5e (6-DOF), and UR10e (6-DOF) -- totaling over 50,000 experiments. Our logistic regression risk model achieves AUC 0.780 and identifies a closed-form failure boundary equation. We further benchmark eight VLA (Vision-Language-Action) policies, including a fine-tuned NVIDIA GR00T N1.6 (3B) trained on LIBERO-Spatial for 20K steps. The same checkpoint achieves 97.65% success rate on LIBERO (MuJoCo) but 0% on RoboGate's 68 industrial scenarios in NVIDIA Isaac Sim -- a 97.65 percentage point cross-simulator gap on a single model that underscores the deployment validation challenge. Inspired by the validation-layer paradigm NVIDIA codified for quantum computing with Ising, ROBOGATE provides this validation layer for Physical AI. Open-source.

Deploying learned robot manipulation policies in industrial settings requires rigorous pre-deployment validation, yet exhaustive testing across high-dimensional parameter spaces is intractable.

Post-training quantization (PTQ) is essential for deploying large diffusion transformers on resource-constrained hardware, but aggressive 4-bit quantization significantly degrades generative performance. Low-rank approximation methods have emerged as a promising solution by appending auxiliary linear branches to restore performance. However, current state-of-the-art approaches assume these branches must retain high precision (W16A16) and rely on heavy, data-dependent calibration for initialization. We challenge both limitations with LoRaQ (Low-Rank Approximated Quantization), a simple, data-free calibration approach that optimizes quantization error compensation. By overcoming the need for high-precision branches, LoRaQ enables the first fully sub-16 bit pipeline, allowing the low-rank branch itself to be quantized. We demonstrate that, at equal memory overhead, LoRaQ outperforms the state-of-the-art methods in their native implementations on Pixart-$Σ$ and SANA. We also analyze mixed-precision configurations, showing that setups such as W8A8, W6A6, and W4A8 for the low-rank branch, alongside a W4 main layer, yield superior results while maintaining a fully quantized architecture compatible with modern mixed-precision hardware.

Post-training quantization (PTQ) is essential for deploying large diffusion transformers on resource-constrained hardware, but aggressive 4-bit quantization significantly degrades generative performance.

Autonomous planetary exploration demands real-time, high-fidelity environmental perception. Standard deep learning models require massive computational resources. Conversely, space-qualified onboard computers operate under strict power, thermal, and memory limits. This disparity creates a severe engineering bottleneck, preventing the deployment of highly capable perception architectures on extraterrestrial exploration platforms. In this foundational concept paper, we propose the theoretical architecture for the Adaptive Quantized Planetary Crater Detection System (AQ-PCDSys) to resolve this bottleneck. We present a mathematical blueprint integrating an INT8 Quantized Neural Network (QNN) designed specifically for Quantization Aware Training (QAT). To address sensor fragility, we mathematically formalize an Adaptive Multi-Sensor Fusion (AMF) module. By deriving the exact integer requantization multiplier required for spatial attention gating, this module actively selects and fuses Optical Imagery (OI) and Digital Elevation Models (DEMs) at the feature level, ensuring reliable perception during extreme cross-illuminations and optical hardware dropouts. Furthermore, the architecture introduces anchor-free, center-to-edge regression heads, protected by a localized FP16 coordinate conversion, to accurately frame asymmetrical lunar craters without catastrophic integer truncation. Rather than presenting physical hardware telemetry, this manuscript establishes the theoretical bounds, structural logic, and mathematical justifications for the architecture. We outline a rigorous Hardware-in-the-Loop (HITL) evaluation protocol to define the exact testing criteria required for future empirical validation, paving the way for next-generation space-mission software design.

Autonomous planetary exploration demands real-time, high-fidelity environmental perception.

Recent Vision-Language-Action (VLA) models report impressive success rates on standard robotic benchmarks, fueling optimism about general-purpose physical intelligence. However, recent evidence suggests a systematic misalignment between standard benchmark success and true embodied reasoning, raising the question of whether these high scores reflect genuine cognitive capability. To address this gap, we introduce BeTTER, a diagnostic Benchmark for Testing True Embodied Reasoning in robotic policies. BeTTER applies targeted causal interventions (e.g., spatial layout shifts, temporal extrapolation) while enforcing kinematic isolation to explicitly decouple high-level reasoning failures from low-level execution limits. Through systematic evaluation, we reveal that state-of-the-art VLAs catastrophically fail in dynamic scenarios, exhibiting severe lexical-kinematic shortcuts, behavioral inertia, and semantic feature collapse. Crucially, our mechanistic analysis traces these symptoms to fundamental architectural bottlenecks - such as capacity compression and myopic downsampling - which systematically degrade the model's foundational semantic representation. We demonstrate that highly static evaluation protocols effectively mask this degradation by allowing optimization to overfit to sensorimotor priors. Supported by real-world robotic validation, our findings confirm that this representational breakdown is not a simulation artifact, highlighting the critical need for future VLA paradigms to resolve the structural tension between high-frequency control and high-level reasoning.

Recent Vision-Language-Action (VLA) models report impressive success rates on standard robotic benchmarks, fueling optimism about general-purpose physical intelligence.

Robotic task planning in real-world environments requires reasoning over implicit constraints from language and vision. While LLMs and VLMs offer strong priors, they struggle with long-horizon structure and symbolic grounding. Existing methods that combine LLMs with symbolic planning often rely on handcrafted or narrow domains, limiting generalization. We propose UniDomain, a framework that pre-trains a PDDL domain from robot manipulation demonstrations and applies it for online robotic task planning. It extracts atomic domains from 12,393 manipulation videos to form a unified domain with 3137 operators, 2875 predicates, and 16481 causal edges. Given a target class of tasks, it retrieves relevant atomics from the unified domain and systematically fuses them into high-quality meta-domains to support compositional generalization in planning. Experiments on diverse real-world tasks show that UniDomain solves complex, unseen tasks in a zero-shot manner, achieving up to 58% higher task success and 160% improvement in plan optimality over state-of-the-art LLM and LLM-PDDL baselines.

Robotic task planning in real-world environments requires reasoning over implicit constraints from language and vision.

Human interaction is inherently multimodal and full-duplex: we listen while watching, speak while acting, and fluidly adapt to turn-taking and interruptions. Realizing these capabilities is essential for building models simulating humans. We present ELLSA (End-to-end Listen, Look, Speak and Act), which, to our knowledge, is the first full-duplex, end-to-end model that simultaneously perceives and generates across vision, text, speech, and action within a single architecture, enabling interaction patterns previously out of reach, yielding more natural, human-like behaviors. At its core is a novel SA-MoE architecture (Self-Attention Mixture-of-Experts) that routes each modality to specialized experts and fuses them through a unified attention backbone. This provides a generalizable solution for joint multimodal perception and concurrent generation, leveraging strong pre-trained components while enabling efficient modality integration and mitigating modality interference. On speech-interaction and robot-manipulation benchmarks, ELLSA matches modality-specific baselines, while uniquely supporting advanced multimodal and full-duplex behaviors such as dialogue and action turn-taking, defective instruction rejection, speaking-while-acting, context-grounded visual question answering, and action barge-ins. We contend that ELLSA represents a step toward more natural and general interactive intelligence, contributing to the broader pursuit of artificial general intelligence. All data, code and model checkpoints will be released at https://github.com/bytedance/SALMONN/tree/ELLSA.

Human interaction is inherently multimodal and full-duplex: we listen while watching, speak while acting, and fluidly adapt to turn-taking and interruptions.

Vision-Language-Action (VLA) models map multimodal inputs directly to robot actions and are typically trained through large-scale imitation learning. While this paradigm has shown strong performance, prevailing VLA training procedures do not explicitly supervise hard physical constraints such as obstacle avoidance or kinematic feasibility. As a result, the geometric structure underlying physically feasible behavior must be inferred only implicitly from demonstrations. In this paper, we study whether introducing explicit feasibility supervision can provide effective structured guidance for VLA policies. We formulate a simple geometry-grounded feasibility objective and integrate it into the training stage of a diffusion-based VLA policy. To evaluate this idea systematically, we use obstacle-aware manipulation as a controlled probe of geometry-dependent physical feasibility. Empirical results show that augmenting VLA training with feasibility supervision improves both physical reliability and overall task performance, while also enhancing learning efficiency in the low-data regime. These findings indicate that explicit feasibility signals can effectively complement imitation-based VLA learning, highlighting their potential for developing more reliable VLA policies.

Vision-Language-Action (VLA) models map multimodal inputs directly to robot actions and are typically trained through large-scale imitation learning.

Inverse Dynamics Models (IDMs) map visual observations to low-level action commands, serving as central components for data labeling and policy execution in embodied AI. However, their performance degrades severely under manipulator truncation, a common failure mode that makes state recovery ill-posed and leads to unstable control. We present StableIDM, a spatio-temporal framework that refines features from visual inputs to stabilize action predictions under such partial observability. StableIDM integrates three complementary components: (1) auxiliary robot-centric masking to suppress background clutter, (2) Directional Feature Aggregation (DFA) for geometry-aware spatial reasoning, which extracts anisotropic features along directions inferred from the visible arm and (3) Temporal Dynamics Refinement (TDR) to smooth and correct predictions via motion continuity. Extensive evaluations validate our approach: StableIDM improves strict action accuracy by 12.1% under severe truncation on the AgiBot benchmark, and increases average task success by 9.7% in real-robot replay. Moreover, it boosts end-to-end grasp success by 11.5% when decoding video-generated plans, and improves downstream VLA real-robot success by 17.6% when functioning as an automatic annotator. These results demonstrate that StableIDM provides a robust and scalable backbone for both policy execution and data generation in embodied artificial intelligence.

Inverse Dynamics Models (IDMs) map visual observations to low-level action commands, serving as central components for data labeling and policy execution in embodied AI.

Vision-language-action (VLA) models have achieved great success on general robotic tasks, but still face challenges in fine-grained spatiotemporal manipulation. Typically, existing methods mainly embed spatiotemporal knowledge into visual and action representations, and directly perform a cross-modal mapping for step-level action prediction. However, such spatiotemporal reasoning remains largely implicit, making it difficult to handle multiple sequential behaviors with explicit spatiotemporal boundaries. In this work, we propose ST-$π$, a structured spatiotemporal VLA model for robotic manipulation. Our model is guided by two key designs: 1) Spatiotemporal VLM. We encode 4D observations and task instructions into latent spaces, and feed them into the LLM to generate a sequence of causally ordered chunk-level action prompts consisting of sub-tasks, spatial grounding and temporal grounding. 2) Spatiotemporal action expert. Conditioned on chunk-level action prompts, we design a structured dual-generator guidance to jointly model spatial dependencies and temporal causality, thus predicting step-level action parameters. Within this structured framework, the VLM explicitly plans global spatiotemporal behavior, and the action expert further refines local spatiotemporal control. In addition, we propose a real-world robotic dataset with structured spatiotemporal annotations for fine-tuning. Extensive experiments have been conducted to demonstrate the effectiveness of our model. Our code link: https://github.com/chuanhaoma/ST-pi.

Vision-language-action (VLA) models have achieved great success on general robotic tasks, but still face challenges in fine-grained spatiotemporal manipulation.

Robust robotic manipulation requires not only predicting how the scene evolves over time, but also recognizing task-relevant objects in complex scenes. However, existing VLA models face two limitations. They typically act only on the current frame, while future prediction and object-aware reasoning are often learned in separate latent spaces. We propose OFlow (injecting Object-Aware Temporal Flow Matching into VLAs), a framework that addresses both limitations by unifying temporal foresight and object-aware reasoning in a shared semantic latent space. Our method forecasts future latents with temporal flow matching, factorizes them into object-aware representations that emphasize physically relevant cues while filtering task-irrelevant variation, and conditions continuous action generation on these predictions. By integrating OFlow into VLA pipelines, our method enables more reliable control under distribution shifts. Extensive experiments across LIBERO, LIBERO-Plus, MetaWorld, and SimplerEnv benchmarks and real-world tasks demonstrate that object-aware foresight consistently enhances robustness and success.

Robust robotic manipulation requires not only predicting how the scene evolves over time, but also recognizing task-relevant objects in complex scenes.

As deep learning-based AI technologies gain momentum, the demand for general-purpose AI computing architectures continues to grow. While GPGPU-based architectures offer versatility for diverse AI workloads, they often fall short in efficiency and cost-effectiveness. Various Domain-Specific Architectures (DSAs) excel at particular AI tasks but struggle to extend across broader applications or adapt to the rapidly evolving AI landscape. M100 is Li Auto's response: a performant, cost-effective architecture for AI inference in Autonomous Driving (AD), Large Language Models (LLMs), and intelligent human interactions, domains crucial to today's most competitive automobile platforms. M100 employs a dataflow parallel architecture, where compiler-architecture co-design orchestrates not only computation but, more critically, data movement across time and space. Leveraging dataflow computing efficiency, our hardware-software co-design improves system performance while reducing hardware complexity and cost. M100 largely eliminates caching: tensor computations are driven by compiler- and runtime-managed data streams flowing between computing elements and on/off-chip memories, yielding greater efficiency and scalability than cache-based systems. Another key principle was selecting the right operational granularity for scheduling, issuing, and execution across compiler, firmware, and hardware. Recognizing commonalities in AI workloads, we chose the tensor as the fundamental data element. M100 demonstrates general AI computing capability across diverse inference applications, including UniAD (for AD) and LLaMA (for LLMs). Benchmarks show M100 outperforms GPGPU architectures in AD applications with higher utilization, representing a promising direction for future general AI computing.

As deep learning-based AI technologies gain momentum, the demand for general-purpose AI computing architectures continues to grow.

Memory pressure has emerged as a dominant constraint in scaling the training of large language models (LLMs), particularly in resource-constrained environments. While modern frameworks incorporate various memory-saving techniques, they often expose low-level configuration knobs that require manual tuning and specialized system expertise. This not only adds engineering overhead but also risks suboptimal hardware utilization when misconfigured. This paper introduces ProTrain, a novel training system that automatically tailors memory management policies to the model architecture and underlying hardware resources, eliminating the need for manual intervention. The core of ProTrain is its automated memory management that abstracts complex memory management strategies into a few tunable configuration parameters, allowing searches for optimal parameter settings using cost models. ProTrain is equipped with a runtime profiler that provides precise estimates of latency, memory usage, and I/O bandwidth to build high-fidelity cost models. ProTrain does not change the training algorithm and thus does not compromise accuracy. Experiments show that ProTrain improves training throughput by 1.43$\times$ to 2.71$\times$ compared to the state-of-the-art training systems.

Memory pressure has emerged as a dominant constraint in scaling the training of large language models (LLMs), particularly in resource-constrained environments.

What appears effortless to a human waiter remains a major challenge for robots. Manipulating objects nonprehensilely on a tray is inherently difficult, and the complexity is amplified in dual-arm settings. Such tasks are highly relevant to service robotics in domains such as hotels and hospitality, where robots must transport and reposition diverse objects with precision. We present DART, a novel dual-arm framework that integrates nonlinear Model Predictive Control (MPC) with an optimization-based impedance controller to achieve accurate object motion relative to a dynamically controlled tray. The framework systematically evaluates three complementary strategies for modeling tray-object dynamics as the state transition function within our MPC formulation: (i) a physics-based analytical model, (ii) an online regression based identification model that adapts in real-time, and (iii) a reinforcement learning-based dynamics model that generalizes across object properties. Our pipeline is validated in simulation with objects of varying mass, geometry, and friction coefficients. Extensive evaluations highlight the trade-offs among the three modeling strategies in terms of settling time, steady-state error, control effort, and generalization across objects. To the best of our knowledge, DART constitutes the first framework for non-prehensile dual-arm manipulation of objects on a tray. Project Link: https://dart-icra.github.io/dart/

What appears effortless to a human waiter remains a major challenge for robots.

Vision-Language-Action (VLA) models have gained much attention from the research community thanks to their strength in translating multimodal observations with linguistic instructions into desired robotic actions. Despite their advancements, VLAs often overlook explicit reasoning and learn the functional input-action mappings, omitting crucial logical steps, which are especially pronounced in interpretability and generalization for complex, long-horizon manipulation tasks. In this work, we propose ReFineVLA, a multimodal reasoning-aware framework that fine-tunes VLAs with teacher-guided reasons. We first augment robotic datasets with reasoning rationales generated by an expert teacher model, guiding VLA models to learn to reason about their actions. Then, we fine-tune pre-trained VLAs with the reasoning-enriched datasets with ReFineVLA, while maintaining the underlying generalization abilities and boosting reasoning capabilities. We also conduct attention map visualization to analyze the alignment among visual observation, linguistic prompts, and to-be-executed actions of ReFineVLA, reflecting the model is ability to focus on relevant tasks and actions. Through this additional step, we explore that ReFineVLA-trained models exhibit a meaningful agreement between vision-language and action domains, highlighting the enhanced multimodal understanding and generalization. Evaluated across a suite of simulated manipulation benchmarks on SimplerEnv with both WidowX and Google Robot tasks, ReFineVLA achieves state-of-the-art performance, in success rate over the second-best method on the both the WidowX benchmark and Google Robot Tasks.

Vision-Language-Action (VLA) models have gained much attention from the research community thanks to their strength in translating multimodal observations with linguistic instructions into desired robotic actions.

The democratization of ubiquitous AI hinges on deploying sophisticated reasoning capabilities on resource-constrained devices. However, Small Language Models (SLMs) often face a "reasoning gap", particularly in non-English languages like Vietnamese, where they struggle to maintain coherent chains of thought. This paper investigates Test-Time Scaling strategies for the Qwen3-1.7B architecture within the context of Vietnamese Elementary Mathematics. We introduce Vi-S1K, a high-fidelity reasoning dataset localized via a Gemini 2.5 Flash-Lite powered pipeline, and Vi-Elementary-Bench, a dual-resource benchmark for rigorous evaluation. Using an LLM-as-a-Judge protocol, we reveal that the base model possesses robust latent knowledge (Accuracy: 4.05/5.00) but suffers from a severe "formatting gap" in communication. Supervised Fine-Tuning (SFT) acts as a critical "reasoning unlocker", yielding a 77% improvement in Explanation Quality and bridging the gap between raw calculation and pedagogical coherence. Furthermore, our analysis of prompting strategies uncovers a significant trade-off: structured frameworks like ReAct impose a "cognitive tax" on the 1.7B parameter capacity, degrading performance relative to pure Chain-of-Thought (CoT) combined with Self-Consistency. These findings establish a deployment hierarchy for SLMs, demonstrating that SFT combined with simplified test-time scaling is superior to complex agentic workflows for edge-based reasoning.

The democratization of ubiquitous AI hinges on deploying sophisticated reasoning capabilities on resource-constrained devices.

Precision-critical manipulation requires both global trajectory organization and local execution correction, yet most vision-language-action (VLA) policies generate actions within a single unified space. This monolithic formulation forces macro-level transport and micro-level refinement to be optimized under the same objective, causing large motions to dominate learning while suppressing small but failure-critical corrective signals. In contrast, human manipulation is structured by global movement planning together with continuous local adjustment during execution. Motivated by this principle, we propose AnchorRefine, a hierarchical framework that factorizes VLA action modeling into trajectory anchor and residual refinement. The anchor planner predicts a coarse motion scaffold, while the refinement module corrects execution-level deviations to improve geometric and contact precision. We further introduce a decision-aware gripper refinement mechanism to better capture the discrete and boundary-sensitive nature of gripper control. Experiments on LIBERO, CALVIN, and real-robot tasks demonstrate that AnchorRefine consistently improves both regression-based and diffusion-based VLA backbones, yielding gains of up to 7.8% in simulation success rate and 18% in real-world success rate.

Precision-critical manipulation requires both global trajectory organization and local execution correction, yet most vision-language-action (VLA) policies generate actions within a single unified space.

This paper considers reinforcement learning from human feedback in a federated learning setting with resource-constrained agents, such as edge devices. We propose an efficient federated RLHF algorithm, named Partitioned, Sign-based Stochastic Zeroth-order Policy Optimization (Par-S$^2$ZPO). The algorithm is built on zeroth-order optimization with binary perturbation, resulting in low communication, computation, and memory complexity by design. Our theoretical analysis establishes an upper bound on the convergence rate of Par-S$^2$ZPO, revealing that it is as efficient as its centralized counterpart in terms of sample complexity but converges faster in terms of policy update iterations. Our experimental results show that it outperforms a FedAvg-based RLHF on four MuJoCo RL tasks.

This paper considers reinforcement learning from human feedback in a federated learning setting with resource-constrained agents, such as edge devices.

Visual-Language-Action (VLA) models represent a paradigm shift in embodied AI, yet existing frameworks often struggle with imprecise spatial perception, suboptimal multimodal fusion, and instability in reinforcement learning. To bridge these gaps, we propose OmniVLA-RL, a novel architecture that leverages a Mix-of-Transformers (MoT) design to synergistically integrate reasoning, spatial, and action experts. Furthermore, we introduce Flow-GSPO, which reformulates flow matching as a Stochastic Differential Equation (SDE) process and integrates it with Group Segmented Policy Optimization (GSPO) to enhance action precision and training robustness. Extensive evaluations on the LIBERO and LIBERO-Plus benchmarks demonstrate that OmniVLA-RL significantly outperforms state-of-the-art methods, effectively overcoming the fundamental limitations of current VLA models.

Visual-Language-Action (VLA) models represent a paradigm shift in embodied AI, yet existing frameworks often struggle with imprecise spatial perception, suboptimal multimodal fusion, and instability in reinforcement learning.

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.