Beyond Thinking: Imagining in 360$^\circ$ for Humanoid Visual Search

• URL: http://arxiv.org/abs/2605.09146v1
• Date: Sat, 09 May 2026 20:10:53 GMT
• Title: Beyond Thinking: Imagining in 360$^\circ$ for Humanoid Visual Search
• Abstract summary: Humanoid Visual Search (HVS) requires agents to actively explore immersive 360$circ$ environments.<n>We propose Imagining in 360$circ$, a novel framework that decouples the exploration process into a specialized Imaginator and an Actor.<n>We show that explicitly modeling semantic spatial priors drastically improves search efficiency and success rates in complex, in-the-wild environments.
• Score: 50.04233606482412
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Humanoid Visual Search (HVS) requires agents to actively explore immersive 360$^\circ$ environments. While prior methods treat this as a monolithic task relying on cumulative, multi-turn Chain-of-Thought (CoT) reasoning, they impose heavy cognitive burdens and require expensive trajectory-level annotations. In this paper, we propose Imagining in 360$^\circ$, a novel framework that decouples the exploration process into a specialized Imaginator and an Actor. The Imaginator functions as a probabilistic predictor of spatial priors; instead of maintaining a cumulative reasoning chain, it infers the semantic layout of both observed and unobserved regions in a single step. By sampling multiple hypotheses within this semantic space, we provide the Actor with a distribution of effective spatial information, offering robust guidance that hedges against uncertainty during active search. This decoupled architecture significantly lowers data engineering costs by eliminating the need for full-trajectory CoT annotations, enabling the generation of over 1.96 million curated training samples. Extensive experiments demonstrate that explicitly modeling semantic spatial priors drastically improves search efficiency and success rates in complex, in-the-wild environments.

Related papers

• Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration [12.531650952835493]
  In this paper, we propose a new paradigm that explicitly separates exploration from exploitation and bypasses RL during the exploration phase.<n>By removing the overhead of policy optimization, our approach explores an order of magnitude more efficiently than standard intrinsic motivation baselines on hard Atari benchmarks.<n>We demonstrate that the discovered trajectories can be distilled into deployable policies using existing supervised backward learning algorithms.
  arXiv  Detail & Related papers  (2026-03-23T17:56:52Z)
• GeoSense: Internalizing Geometric Necessity Perception for Multimodal Reasoning [51.63457948949102]
  We develop a framework to overcome the limited spatial understanding of Multimodal Large Language Models (MLLMs)<n>Our framework endows the model with an awareness of perceptual insufficiency, empowering it to autonomously engage geometric features in reasoning when 2D cues are deemed insufficient.
  arXiv  Detail & Related papers  (2026-03-11T03:32:12Z)
• Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration? [83.13508919229939]
  Theory of Space is defined as an agent's ability to actively acquire information through self-directed, active exploration.<n>A key innovation is spatial belief probing, which prompts models to reveal their internal spatial representations at each step.<n>Our findings suggest that current foundation models struggle to maintain coherent, revisable spatial beliefs during active exploration.
  arXiv  Detail & Related papers  (2026-02-04T19:06:40Z)
• TDMPBC: Self-Imitative Reinforcement Learning for Humanoid Robot Control [26.93901849666341]
  In general, feasible regions for accomplishing tasks within complex high-dimensional spaces are exceedingly narrow.<n>We propose the $textbfS$elf-$textbfI$mitative $textbfR$einforcement, where the RL algorithm also imitates potentially task-relevant trajectories.<n>Our proposed algorithm achieves 120% performance improvement on the challenging HumanoidBench with 5% extra computation overhead.
  arXiv  Detail & Related papers  (2025-02-24T16:55:27Z)
• TrackFlow: Multi-Object Tracking with Normalizing Flows [36.86830078167583]
  We aim at extending tracking-by-detection to multi-modal settings. A rough estimate of 3D information is also available and must be merged with other traditional metrics. Our approach consistently enhances the performance of several tracking-by-detection algorithms.
  arXiv  Detail & Related papers  (2023-08-22T15:40:03Z)
• Calibration of Derivative Pricing Models: a Multi-Agent Reinforcement Learning Perspective [3.626013617212667]
  One of the most fundamental questions in quantitative finance is the existence of continuous-time diffusion models that fit market prices of a given set of options. Our contribution is to show how a suitable game theoretical formulation of this problem can help solve this question by leveraging existing developments in modern deep multi-agent reinforcement learning.
  arXiv  Detail & Related papers  (2022-03-14T05:34:00Z)
• On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game [140.19656665344917]
  We study the reward-free RL problem, where an agent aims to thoroughly explore the environment without any pre-specified reward function. We tackle this problem under the context of function approximation, leveraging powerful function approximators. We establish the first provably efficient reward-free RL algorithm with kernel and neural function approximators.
  arXiv  Detail & Related papers  (2021-10-19T07:26:33Z)
• Batch Exploration with Examples for Scalable Robotic Reinforcement Learning [63.552788688544254]
  Batch Exploration with Examples (BEE) explores relevant regions of the state-space guided by a modest number of human provided images of important states. BEE is able to tackle challenging vision-based manipulation tasks both in simulation and on a real Franka robot.
  arXiv  Detail & Related papers  (2020-10-22T17:49:25Z)
• Evidential Sparsification of Multimodal Latent Spaces in Conditional Variational Autoencoders [63.46738617561255]
  We consider the problem of sparsifying the discrete latent space of a trained conditional variational autoencoder. We use evidential theory to identify the latent classes that receive direct evidence from a particular input condition and filter out those that do not. Experiments on diverse tasks, such as image generation and human behavior prediction, demonstrate the effectiveness of our proposed technique.
  arXiv  Detail & Related papers  (2020-10-19T01:27:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.