5arXiv cs.AI (Artificial Intelligence)·
GROW² framework enables open-world affordance grounding for creative robot tool use
Researchers introduce GROW² (GROunding Which and Where), a hierarchical framework for robot tool use that enables selecting and localizing arbitrary objects as tools beyond their intended functions. The system uses Vision-Language Models for semantic reasoning to identify suitable tools and task-relevant parts, then vision foundation models for geometric grounding into 3D regions from RGB-D images. GROW² achieves zero-shot generalization over open-category objects and outperforms baselines on affordance prediction benchmarks in both simulated and real-world settings, without requiring end-to-end training on large datasets.
Related guides (2)
Related events (8)
TREAD: VLM-based re-labelling framework improves robot policy generalization via dataset augmentation
TREAD (Task Robustness via Re-Labelling Vision-Action Robot Data) is a scalable framework that uses pretrained Vision-Language Models to augment existing robotics datasets without new data collection. The approach decomposes demonstrations into sub-tasks, segments videos accordingly, and generates linguistically diverse instruction labels, enriching language-action pair diversity. Evaluations on the LIBERO benchmark show improved generalization to novel tasks and goals, addressing a key limitation of current robot learning policies.
Geometric Action Model (GAM) repurposes geometric foundation models for 3D-aware robot manipulation
Researchers propose the Geometric Action Model (GAM), a language-conditioned robot manipulation policy that splits a pretrained geometric foundation model (GFM) to serve simultaneously as an observation encoder, causal future predictor, and action decoder. Unlike existing vision-language-action models that operate on 2D image frames, GAM explicitly incorporates 3D geometric priors for contact-rich manipulation. The approach claims improvements in accuracy, robustness, speed, and model size over foundation-model-scale baselines across simulation and real-robot benchmarks.
VLK: Synthetic vision-language-kinematics supervision enables humanoid loco-manipulation from egocentric observations
Researchers introduce a pipeline that generates 48,000 paired vision-language-kinematics trajectories synthetically using 3D Gaussian Splatting to reconstruct indoor scenes, bypassing the need for expensive human-annotated robot data. A VLK policy trained on this data predicts whole-body kinematic trajectories from egocentric images and language instructions, which a whole-body tracker converts to physical actions. The approach is validated on a Unitree G1 humanoid performing navigation and object transport, demonstrating viable sim-to-real transfer for perception-based loco-manipulation.
Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation
This Hugging Face blog post details a workflow for fine-tuning NVIDIA's Cosmos Predict 2.5 world model using LoRA and DoRA parameter-efficient techniques for robot video generation tasks. The post covers practical implementation steps for adapting the foundation video model to robotics-specific domains. This represents a concrete application of world models to embodied AI, where synthetic video generation can support robot training data pipelines.
RoboWits: Benchmark for Robotic Creative Problem Solving Under Unexpected Conditions
RoboWits is a new bi-manual robotic benchmark designed to evaluate cognitive reasoning, creative tool use, and robustness to unexpected conditions in robotics. The authors introduce an automated multi-agent task generation pipeline that produces 30 seed tasks and 208 mutated tasks spanning geometry, material, and assembly-based reasoning. Benchmarking results show that pre-trained Vision-Language-Action models (VLAs) achieve limited success on seed tasks after fine-tuning but fail on mutated variants, exposing brittleness in reasoning and strategy adaptation. The benchmark highlights a significant gap between skill-level execution and genuine cognitive reasoning in current robotic systems.
Cortex: Bidirectionally aligned VLM-VLA framework for long-horizon robot manipulation
Cortex is a new embodied agent framework that bridges the semantic gap between high-level Vision-Language Model (VLM) planning and low-level Vision-Language-Action (VLA) execution for long-horizon robotic manipulation. The system standardizes manipulation into 32 canonical skill primitives and uses an event-balanced sampling strategy to handle subtask transition ambiguity, enabling automatic annotation of over 4,000 hours of video data. Cortex outperforms monolithic baselines by 3.1% on Libero-long and 4.1% on RoboTwin benchmarks, and demonstrates zero-shot generalization to unseen real-world tasks such as multi-stage chemistry experiments.
EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL
EnvFactory is a fully automated framework for training tool-use LLM agents via Agentic Reinforcement Learning, addressing two key bottlenecks: scalable execution environments and realistic multi-turn training data. It autonomously constructs stateful, executable tool environments from authentic resources and synthesizes natural trajectories with implicit human intents via topology-aware sampling. Using only 85 verified environments across 7 domains, it generates 2,575 SFT and RL trajectories and improves Qwen3-series models by up to +15% on BFCLv3, +8.6% on MCP-Atlas, and +6% on conversational benchmarks, outperforming prior approaches that use 5x more environments.
E-TTS: Embodied test-time scaling framework for robotic manipulation with history-aware iterative refinement
Researchers introduce E-TTS, a modular test-time scaling framework for robotic manipulation that unifies reasoning and action scaling via history-aware iterative refinement and vision-language verifiers. The framework addresses two gaps in prior work: underexplored reasoning scaling mechanisms and inadequate use of historical context in long-horizon sequential tasks. Evaluated across 4 benchmarks, 6 environments, 3 embodiments, and 4 base vision-language-action models, E-TTS achieves up to 33.14% improvement in simulation and 26.62% in real-world scenarios without additional expert data or retraining.