Papers

SimpleVLN: Towards Simple and Frontier Vision-Language Navigation

Vision-and-Language Navigation (VLN) requires embodied agents to ground language in visual observations and make long-horizon decisions. Existing methods often address these demands through task-specific architectures. As multimodal large language models (MLLMs) become increasingly capable, an important question remains: Have we truly unlocked the potential of native MLLMs for VLN before introducing task-specific architecture? We present SimpleVLN, an architecture-preserving framework developed through studies of navigation formulation, data construction, and optimization. At the formulation level, SimpleVLN combines single-turn decision inputs with fixed-budget global-local memory to efficiently use navigation history without unbounded context growth, while action chunks enable efficient output of multiple primitive actions per model invocation. For data construction, we combine expert demonstrations with policy-dependent DAgger experience and develop a scalable synthesis pipeline that generates large-scale tasks for reinforcement learning. At the optimization level, a progressive IL-DAgger-RL pipeline advances from action imitation to task-level outcome optimization. Comprehensive experiments validate the effectiveness of these three aspects. We instantiate SimpleVLN across multiple MLLM backbones and model sizes, demonstrating its generality. SimpleVLN achieves 76.7% and 80.1% success rates on the R2R-CE and RxR-CE splits, respectively, substantially outperforming existing methods. These results show that the navigation capabilities of native MLLMs can be effectively unlocked without task-specific architectural designs.

Vision-language navigationEmbodied AI

Lingyi Hong, Weiren Cai, Jiayu Chen · 34 views · Oct 16, 2026

MemoryVLN: From Ego-Aware Memory Representation to Cross-Context Memory Reuse in Vision-Language Navigation

MemoryVLN compresses long navigation histories with forgetting-curve sampling, stamps each memory with 2D appearance, frozen VGGT 3D geometry and 6D ego pose, and manages in-episode plus context-level banks with warm start and confidence-gated write-back; Top-K retrieval then residually enhances the current frame, improving success rate by about 2% on R2R-CE and 6.5% on RxR-CE over the strongest data-comparable baselines.

Vision-language navigationMemory

Xueyao Wei, Yifei Wang, Delun Li · 202 views · Oct 13, 2026

Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies

Evaluates GPT-6 Astra as an embodied policy across six domains: hybrid control reaches 48% on RoboDojo and 92% on RxR navigation, while direct in-hand control and dense locomotion references stay unreliable; token use and inference latency constrain practical control.

Embodied AIRobot Manipulation

Galbot Team, Chen, Xuchuan, Cheng, Xiaoqian · 276 views · Sep 29, 2026

ASENA: Self-evolving Agents for Embodied Navigation

We present ASENA, an embodied agent system that enables general-purpose coding agents to program humanoid navigation, manipulation, and interaction. Through a unified robot harness, agents read sensor data, write and execute programs, inspect recorded outcomes, repair failures, and reuse notes and executable skills while keeping their model weights fixed. We also introduce ASENA-VLN, a 4B monocular navigation policy that serves as an optional tool within this programmable system. ASENA-VLN predicts body-frame trajectories for both extended routes and short-horizon behaviors. Its shared vision-language decoder is trained on route instructions, visual question answering, and a newly curated dataset of geometry-derived atomic navigation tasks. As a standalone policy, ASENA-VLN achieves state-of-the-art success rates of 68.7% on R2R and 70.2% on RxR. When integrated with a coding agent, learned navigation improves ASENA's success rate by 11 percentage points on both agentic benchmarks and reduces execution time. Persistent workspace evolution uses simulator feedback to improve success over ten passes through recurring 100-task subsets. Success increases from 72% to 98% on R2R and from 65% to 89% on RxR. On embodied question answering, ASENA achieves state-of-the-art accuracy with fewer interaction steps. On a Unitree G1, we demonstrate search, visual inspection, spatial reasoning, synthesized gestures, and mobile manipulation combining object pickup, carrying, and handoff without a pre-built map. These demonstrations illustrate how online programming extends robot behavior beyond route following and predefined skills.

Vision-language navigationEmbodied AI

An-Chieh Cheng, Isabella Liu, Edmund Bu · 212 views · Sep 30, 2026

LifelongCrossNav: Persistent 3D Semantic Memory for Cross-Floor Multi-Object Navigation

Object-goal navigation has made substantial progress in semantic perception and exploration, yet persistent memory for multi-object navigation and cross-floor navigation are still commonly addressed separately. We present LifelongCrossNav, a framework for sequential multi-object ObjectNav in unknown multi-floor indoor environments. Within each episode, the agent receives an ordered sequence of object-goal queries while continuously maintaining a shared sparse 3D semantic voxel memory. This memory incrementally accumulates geometric structure, traversability states, and vision-language features, allowing subsequent object-goal queries to retrieve previously acquired scene information without rebuilding the map. To support persistent search across floors, LifelongCrossNav combines support-aware 3D traversability mapping, stair-specific perception, and direction-aware stair traversal. A unified navigation policy coordinates same-floor frontier exploration, live and historical point-of-interest retrieval, stair navigation, and target-object search and approach. We further introduce HM3D-MFMON, a benchmark for sequential Multi-Floor Multi-Object Navigation built on HM3D scenes, including a dedicated subset in which completing the full sequence of object-goal subtasks requires at least one floor transition. Experimental results show that LifelongCrossNav consistently outperforms a representative planar persistent semantic-map baseline on HM3D-MFMON, demonstrating that persistent 3D semantic memory and cross-floor traversability modeling effectively support sequential multi-object navigation in multi-floor environments. Project page: https://flageval-baai.github.io/LifelongCrossNavPage.

Object-Goal NavigationSemantic Memory

Zehui Li, Zihao Sun, Jiawei Xu · 262 views · Aug 7, 2026

In-Context Learning for Robots: Methods and Applications

General-purpose robots must infer what a new task requires and translate that understanding into appropriate physical action. In-context learning (ICL) for robots supports this process by using demonstrations and interaction to direct existing competence with neural parameters held fixed during deployment. We organize this literature review around the interfaces connecting contextual evidence to execution, distinguishing four families: context-conditioned policies, geometric demonstration transfer, world-model-based control, and skill- and agent-based execution. Comparing these interfaces clarifies their transfer assumptions and the roles of training, correspondence, and memory in making context useful. Across manipulation and navigation, we examine how these mechanisms preserve taught requirements as objects, environments, and execution conditions change. This analysis links method design to evaluation practices that distinguish responsiveness to teaching, physical transfer, and benefits from retained experience. The resulting agenda connects compositional task acquisition and faithful transfer with physical recursive self-improvement, in which experience improves the ability to learn subsequent tasks.

In-Context LearningRobot Learning

Huang, Haojian, Li, Zexi, Guo, Junhao · 262 views · Sep 28, 2026

See-and-Reach: Precise Vision-Language Navigation for UAVs within the Field of View

UAV Vision-Language Navigation (UAV-VLN) is typically formulated as a holistic search-and-reach problem, where long-range target discovery and final target approach are optimized and evaluated jointly. This formulation makes it difficult to assess a critical capability of aerial embodied agents, namely whether a UAV can accurately ground a visible target and translate vision-language evidence into precise 3D motion once the target enters its field of view. To address this limitation, we introduce UAV-VLN-FOV, a target-visible navigation task that isolates the see-and-reach stage and enables a more diagnostic evaluation of terminal reaching ability. We further propose 3DG-VLN, a vision-language waypoint prediction framework guided by dynamic 3D direction cues to enhance fine-grained visual grounding and spatial direction alignment for precise target reaching. Specifically, 3DG-VLN adaptively processes high-resolution front-view and downward-view observations to preserve fine-grained visual and geometric details for target grounding. It also updates the target-relative direction online during closed-loop navigation, allowing the agent to maintain spatial alignment with the target and reduce accumulated direction drift. To support this task, we construct a dedicated high-resolution benchmark which contains 2,717 trajectories with target-oriented high-level instructions, high-resolution front-view and downward-view egocentric observations, and continuous 3D waypoint annotations. Experiments show that 3DG-VLN outperforms competitive UAV-VLN baselines, achieving a 13.82% improvement in success rate. Real-world trials further demonstrate the potential of 3DG-VLN for practical see-and-reach navigation. The source code and benchmark are available at https://github.com/xuefanfu/3DG-VLN.

Vision-language navigationUAV

Fanfu Xue, En Yu, Yantian Shen · 184 views · Jun 18, 2026

Exposing the Long-tail in Embodied Urban Navigation via Scalable Learning from In-the-Wild Videos

Learning embodied urban navigation policies from real-world data is constrained by the cost of task-specific data collection and the limited coverage of rare yet safety-critical scenarios. To address these challenges, we present a scalable framework for learning point-goal urban navigation from web-scale in-the-wild egocentric videos while systematically exposing its long tail. The framework automatically annotates uncurated web videos with metric trajectories and structured navigation semantics, which are then used to train a vision-language-action policy for interpretable navigation planning. We characterize the long tail based on model performance and the distribution of perception-motion patterns, and employ reflection-based analysis to diagnose recurring failure modes. Experiments on web-video data and real-world urban navigation tasks demonstrate effective knowledge transfer from unconstrained videos and reveal coherent long-tail structures beyond aggregate navigation performance.

Urban NavigationVLA

Bingyi Xia, Han Bao, Zhewei Chen · 213 views · Aug 17, 2026

AgentGarten: Code Worlds for Evolving Agents

Interactive virtual worlds allow agents to learn through exploration and interaction. What agents can learn is bounded by the environments they practice in, which must be faithful, with consistent state, rules, and dynamics, and realistic, with observations that follow the real-world visual distributions. Achieving both across diverse worlds remains a bottleneck. We introduce AgentGarten, a framework that couples simulators and game engines with a shared neural renderer to build real-time interactive environments. Its simulation backends maintain persistent world state and execute program-defined interaction rules, while the renderer generates visual observations from structured conditions exported through a common interface. To build the neural renderer, we adapt a pretrained video model to geometry conditions, distill it with our proposed Adversarial Forcing, and optimize inference for real-time interaction. Adversarial Forcing makes history prefilling differentiable through exact replay, so that losses on later predictions update how the renderer encodes prior observations, and adds real-data adversarial supervision to improve its visual quality. In AgentGarten, agents perceive the world through visual observations, interact with it in real time, and improve by distilling each round of experience into playbooks that subsequent agents inherit and refine. Our empirical study demonstrates a substantial gain in learning efficiency, with agents learning from just 4 rounds compared with millions for a conventional reinforcement learning counterpart. As new worlds can be written as code and rendered through the same interface, environments can scale in both number and difficulty alongside their agents, a step toward agents that keep evolving through interactive experience.

World ModelsNeural rendering

Jiawei Chi, Shangchen Miao, Zhiyuan Shi · 477 views · Oct 8, 2026

SparseVideoNav: Real-Time Navigation Video Generation with Sparse Historical Conditioning

SparseVideoNav from OpenDriveLab, HKU and collaborators replaces dense full-frame conditioning with sparse history frames (1, 2, 5, 8) for navigation video generation: latent concatenation plus a zero-initialized history cross-attention branch preserves long-horizon memory, and a three-stage curriculum (full-frame pretraining, sparse fine-tuning, PCM distillation) compresses sampling to 4 steps with 0.4 s per-frame latency, 21% lower FVD than the strongest baseline, and behavior-cloning success lifted from 54% to 67% by generated variants.

World ModelsNavigation

Hai Zhang, Siqi Liang, Li Chen · 454 views · Feb 5, 2026

One Policy, Many Embodiments: Unified Camera-Centric Action Geometry Pre-training for Heterogeneous Embodied Manipulation

UCAG-P from Xiaomi Embodied Intelligence and University of Macau unifies robot arms, bimanual platforms, humanoids and human-hand videos into one camera-centric action schema: 3D camera-frame anchor trajectories of the wrist (p0) and grasp center (p1), with a geometry-conditioned translator emitting executable commands — no retargeting or human-to-robot video synthesis needed. Built on Qwen3-VL-4B with three-stage training over 1.02M episodes / 6,373.6 hours / nine embodiments (36.7% human data), a single checkpoint without benchmark fine-tuning reaches 98.3% on LIBERO, 88.7%/89.2% on RoboTwin Easy/Hard, 82.0% zero-shot on LIBERO-Plus and 62.0% on RoboCasa GR-1; on real Piper robots bread pickup hits 60% vs 20% for pi0.5, with 35% zero-shot ALOHA-to-ARX transfer.

VLACross-Embodiment

Xiaomi Embodied Intelligence Team, University of Macau, : · 656 views · Aug 26, 2026

HAM-VLN: Harnessing Hierarchical Agentic Memory for Zero-Shot Vision-and-Language Navigation

Vision-and-language navigation (VLN) enables robots to follow instructions in previously unseen environments. Recently, a training-free paradigm has emerged: the robot queries a multimodal LLM to understand its observations and plan the next action. However, long-horizon navigation based on either image streams or dense map inevitably introduces a growing memory and reasoning bottleneck. We present HAM-VLN, a decision-coupled, agent-authored memory that equips the robot with a persistent, depth-grounded world graph. In the same model call used to select the next action, HAM-VLN also records semantic and reflective information—including room type, objects, navigation progress, and failure notes. Recent waypoints remain verbatim within a bounded window, while older history re-enters the context only through retrieval scored by relevance, recency, and salience, together with one-hop topological expansion. This design requires no additional LLM calls beyond the per-waypoint decision. Compared to previous methods, HAM-VLN not only improves various navigation metrics but also reduces the context length by more than 65%. Specifically, HAM-VLN achieves 61.0% Success Rate (SR) on VLN-CE R2R, 52.7% SR on VLN-CE RxR, and 79.7% SR on HM3D-v2 ObjectNav without any training.

Vision-language navigationEmbodied AI

An Liu, Bingxi Liu, Hongyu Ding · 725 views · Jul 31, 2026

As an Amazon Associate, we earn from qualifying purchases.