arXiv subjects

Heng Dong

Publications and source records attributed to Heng Dong.

At least 19 recordsLinked to original sources

arXiv2026

GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?

Spatial intelligence is fundamental to embodied agents, yet existing benchmarks focus on local spatial perception from single or few viewpoints, overlooking global spatial awareness over continuous, long-horizon visual streams. To address this limitation, we introduce the Global-Spatial-Temporal Benchmark (GST-Bench), a VQA benchmark for global spatial intelligence in video understanding, comprising human-verified questions derived from 6,790 minutes of synthetically generated video. It requires models to perform accurate spatial inference from novel viewpoints unseen in the input video and to map egocentric observations onto global top-down images. A comprehensive evaluation of 22 state-of-the-art VLMs exposes a striking gap between models and humans: the strongest zero-shot model attains only 42.68, far below the human score of 79.08. To probe the cause of this gap, we construct GST-Bench-Local and find that models, despite strong local spatial understanding under the same task formulation, still fail to consolidate long-horizon observations into a globally consistent scene representation. We further provide GST-Train, a dataset for global spatial reasoning, as a complementary resource to facilitate future research on this challenge.

cs.CV↗

arXiv2026

Hydra-Nav: Object Navigation via Adaptive Dual-Process Reasoning

While large vision-language models (VLMs) show promise for object goal navigation, current methods still struggle with low success rates and inefficient localization of unseen objects--failures primarily attributed to weak temporal-spatial reasoning. Meanwhile, recent attempts to inject reasoning into VLM-based agents improve success rates but incur substantial computational overhead. To address both the ineffectiveness and inefficiency of existing approaches, we introduce Hydra-Nav, a unified VLM architecture that adaptively switches between a deliberative slow system for analyzing exploration history and formulating high-level plans, and a reactive fast system for efficient execution. We train Hydra-Nav through a three-stage curriculum: (i) spatial-action alignment to strengthen trajectory planning, (ii) memory-reasoning integration to enhance temporal-spatial reasoning over long-horizon exploration, and (iii) iterative rejection fine-tuning to enable selective reasoning at critical decision points. Extensive experiments demonstrate that Hydra-Nav achieves state-of-the-art performance on the HM3D, MP3D, and OVON benchmarks, outperforming the second-best methods by 11.1%, 17.4%, and 21.2%, respectively. Furthermore, we introduce SOT (Success weighted by Operation Time), a new metric to measure search efficiency across VLMs with varying reasoning intensity. Results show that adaptive reasoning significantly enhances search efficiency over fixed-frequency baselines.

cs.RO↗

arXiv2026

ROMA: Real-time Omni-Multimodal Assistant with Interactive Streaming Understanding

Recent Omni-multimodal Large Language Models show promise in unified audio, vision, and text modeling. However, streaming audio-video understanding remains challenging, as existing approaches suffer from disjointed capabilities: they typically exhibit incomplete modality support or lack autonomous proactive monitoring. To address this, we present ROMA, a real-time omni-multimodal assistant for unified reactive and proactive interaction. ROMA processes continuous inputs as synchronized multimodal units, aligning dense audio with discrete video frames to handle granularity mismatches. For online decision-making, we introduce a lightweight speak head that decouples response initiation from generation to ensure precise triggering without task conflict. We train ROMA with a curated streaming dataset and a two-stage curriculum that progressively optimizes for streaming format adaptation and proactive responsiveness. To standardize the fragmented evaluation landscape, we reorganize diverse benchmarks into a unified suite covering both proactive (alert, narration) and reactive (QA) settings. Extensive experiments across 12 benchmarks demonstrate ROMA achieves state-of-the-art performance on proactive tasks while competitive in reactive settings, validating its robustness in unified real-time omni-multimodal understanding.

cs.CV↗

arXiv2026

Learning from Mistakes: Negative Reasoning Samples Enhance Out-of-Domain Generalization

Supervised fine-tuning (SFT) on chain-of-thought (CoT) trajectories demonstrations is a common approach for enabling reasoning in large language models. Standard practices typically only retain trajectories with correct final answers (positives) while ignoring the rest (negatives). We argue that this paradigm discards substantial supervision and exacerbates overfitting, limiting out-of-domain (OOD) generalization. Specifically, we surprisingly find that incorporating negative trajectories into SFT yields substantial OOD generalization gains over positive-only training, as these trajectories often retain valid intermediate reasoning despite incorrect final answers. To understand this effect in depth, we systematically analyze data, training dynamics, and inference behavior, identifying 22 recurring patterns in negative chains that serve a dual role: they moderate loss descent to mitigate overfitting during training and boost policy entropy by 35.67% during inference to facilitate exploration. Motivated by these observations, we further propose Gain-based LOss Weighting (GLOW), an adaptive, sample-aware scheme that exploits such distinctive training dynamics by rescaling per-sample loss based on inter-epoch progress. Empirically, GLOW efficiently leverages unfiltered trajectories, yielding a 5.51% OOD gain over positive-only SFT on Qwen2.5-7B and boosting MMLU from 72.82% to 76.47% as an RL initialization.

cs.CL↗

arXiv2025

Robix: A Unified Model for Robot Interaction, Reasoning and Planning

We introduce Robix, a unified model that integrates robot reasoning, task planning, and natural language interaction within a single vision-language architecture. Acting as the high-level cognitive layer in a hierarchical robot system, Robix dynamically generates atomic commands for the low-level controller and verbal responses for human interaction, enabling robots to follow complex instructions, plan long-horizon tasks, and interact naturally with human within an end-to-end framework. Robix further introduces novel capabilities such as proactive dialogue, real-time interruption handling, and context-aware commonsense reasoning during task execution. At its core, Robix leverages chain-of-thought reasoning and adopts a three-stage training strategy: (1) continued pretraining to enhance foundational embodied reasoning abilities including 3D spatial understanding, visual grounding, and task-centric reasoning; (2) supervised finetuning to model human-robot interaction and task planning as a unified reasoning-action sequence; and (3) reinforcement learning to improve reasoning-action consistency and long-horizon task coherence. Extensive experiments demonstrate that Robix outperforms both open-source and commercial baselines (e.g., GPT-4o and Gemini 2.5 Pro) in interactive task execution, demonstrating strong generalization across diverse instruction types (e.g., open-ended, multi-stage, constrained, invalid, and interrupted) and various user-involved tasks such as table bussing, grocery shopping, and dietary filtering.

cs.AI↗

arXiv2025

Dual Orthogonal Projections for Multiuser Interference Cancellation in mmWave Beamforming With Uniform Planar Arrays

This paper investigates multiuser interference (MUI) cancellation for millimeter-wave (mmWave) beamforming in communication systems. We propose a linear algorithm, termed iterative dual orthogonal projections (DOP), which alternates between two orthogonal projections: one to eliminate MUI and the other to refine combiners, ensuring empirical convergence in spectral efficiency. Simulation results show that, with each iteration, the spectral efficiency of each user converges rapidly, closely approaching the theoretical optimum determined by dirty paper coding (DPC), surpassing existing linear benchmarks while maintaining low computational complexity. Furthermore, the proposed DOP algorithm is extended to support both fully-digital and hybrid beamforming architectures.

eess.SP↗

arXiv2025

GPI-Net: Gestalt-Guided Parallel Interaction Network via Orthogonal Geometric Consistency for Robust Point Cloud Registration

The accurate identification of high-quality correspondences is a prerequisite task in feature-based point cloud registration. However, it is extremely challenging to handle the fusion of local and global features due to feature redundancy and complex spatial relationships. Given that Gestalt principles provide key advantages in analyzing local and global relationships, we propose a novel Gestalt-guided Parallel Interaction Network via orthogonal geometric consistency (GPI-Net) in this paper. It utilizes Gestalt principles to facilitate complementary communication between local and global information. Specifically, we introduce an orthogonal integration strategy to optimally reduce redundant information and generate a more compact global structure for high-quality correspondences. To capture geometric features in correspondences, we leverage a Gestalt Feature Attention (GFA) block through a hybrid utilization of self-attention and cross-attention mechanisms. Furthermore, to facilitate the integration of local detail information into the global structure, we design an innovative Dual-path Multi-Granularity parallel interaction aggregation (DMG) block to promote information exchange across different granularities. Extensive experiments on various challenging tasks demonstrate the superior performance of our proposed GPI-Net in comparison to existing methods. The code will be released at https://github.com/gwk429/GPI-Net.

cs.CV↗

arXiv2025

AREE-Based Decoupled Design of Hybrid Beamformers in mmWave XL-MIMO Systems

Hybrid beamforming has been widely employed in mmWave communications such as vehicular-to-everything (V2X) scenarios, as a compromise between hardware complexity and spectral efficiency. However, the inherent coupling between analog and digital precoders in hybrid array architecture significantly limits the computational and spectral efficiency of existing algorithms. To address this issue, we propose an alternating residual error elimination (AREE) algorithm, which decomposes the hybrid beamforming problem into two low-dimensional subproblems, each exhibiting a favorable matrix structure that enables effective decoupling of analog and digital precoders from the matrix product formulation. These subproblems iteratively eliminate each other's residual errors, driving the original problem toward the optimal hybrid beamforming performance. The proposed initialization ensures rapid convergence, while a low-complexity geometric channel SVD algorithm is developed by transforming the high-dimensional sparse channel into a low-dimensional equivalent, thereby simplifying the derivation of subproblems. Simulation results demonstrate that the AREE algorithm effectively decouples analog and digital precoders with low complexity, achieves fast convergence, and offers higher spectral efficiency than existing beamforming methods.

eess.SP↗

arXiv2025

Enhancing Decision-Making of Large Language Models via Actor-Critic

Large Language Models (LLMs) have achieved remarkable advancements in natural language processing tasks, yet they encounter challenges in complex decision-making scenarios that require long-term reasoning and alignment with high-level objectives. Existing methods either rely on short-term auto-regressive action generation or face limitations in accurately simulating rollouts and assessing outcomes, leading to sub-optimal decisions. This paper introduces a novel LLM-based Actor-Critic framework, termed LAC, that effectively improves LLM policies with long-term action evaluations in a principled and scalable way. Our approach addresses two key challenges: (1) extracting robust action evaluations by computing Q-values via token logits associated with positive/negative outcomes, enhanced by future trajectory rollouts and reasoning; and (2) enabling efficient policy improvement through a gradient-free mechanism. Experiments across diverse environments -- including high-level decision-making (ALFWorld), low-level action spaces (BabyAI-Text), and large action spaces (WebShop) -- demonstrate the framework's generality and superiority over state-of-the-art methods. Notably, our approach achieves competitive performance using 7B/8B parameter LLMs, even outperforming baseline methods employing GPT-4 in complex tasks. These results underscore the potential of integrating structured policy optimization with LLMs' intrinsic knowledge to advance decision-making capabilities in multi-step environments.

cs.CL↗

arXiv2025

The Point, the Vision and the Text: Does Point Cloud Boost Spatial Reasoning of Large Language Models? A Bias-Controlled Study

3D Large Language Models (LLMs) leveraging spatial information in point clouds for 3D spatial reasoning attract great attention. Despite some promising results, the advantages of point clouds over other modalities remain unclear. Moreover, existing 3D benchmarks are insufficient for fairly evaluating the ability of multimodal LLMs to comprehend spatial concepts. To address these challenges, we introduce ScanReQA, a 3D spatial reasoning benchmark encompassing text, vision, and point cloud modalities. We then evaluate the performance of text, 2D, and 3D LLMs on the benchmark to compare the effectiveness of different modalities in understanding spatial concepts. Furthermore, we analyze the reasoning mechanisms behind 3D LLMs using point clouds. Our findings reveal that: 1) binary spatial reasoning remains challenging for current 3D LLMs, 2) MLLMs based on point cloud and visual modalities demonstrate stronger spatial reasoning capabilities than LLMs, and 3) 3D LLMs exhibit the attention sink phenomenon similar to that in 2D LLMs, impairing spatial reasoning. We think these conclusions can help the next step of 3D LLMs and also offer insights for foundation models in other modalities. We release datasets and codes in the project page: https://github.com/EmbodiedCity/ScanReQA.code.

cs.CV↗

arXiv2025

Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations

As humans increasingly share environments with diverse agents powered by RL, LLMs, and beyond, the ability to explain agent policies in natural language is vital for reliable coexistence. We introduce a general-purpose framework that trains explanation-generating LLMs via reinforcement learning from AI feedback, with distributional rewards generated by generative continuous normalizing flows (CNFs). CNFs capture the pluralistic and probabilistic nature of human judgments about explanations. Moreover, under mild assumptions, CNFs provably bound deviations from true human reward distributions when trained on noisy proxy rewards from LLMs. We design a specialized CNF architecture that selectively attends to linguistic cues in the decision context and explanations when generating rewards. Human and LLM evaluators find that our method delivers explanations that enable more accurate predictions of true agent decisions, exhibit greater logical soundness and actionability, and impose lower cognitive load than explanations trained with proxy LLM rewards or state-of-the-art RLHF and RLAIF baselines.

cs.CL↗

arXiv2024

On Diffusion Models for Multi-Agent Partial Observability: Shared Attractors, Error Bounds, and Composite Flow

Multiagent systems grapple with partial observability (PO), and the decentralized POMDP (Dec-POMDP) model highlights the fundamental nature of this challenge. Whereas recent approaches to addressing PO have appealed to deep learning models, providing a rigorous understanding of how these models and their approximation errors affect agents' handling of PO and their interactions remain a challenge. In addressing this challenge, we investigate reconstructing global states from local action-observation histories in Dec-POMDPs using diffusion models. We first find that diffusion models conditioned on local history represent possible states as stable fixed points. In collectively observable (CO) Dec-POMDPs, individual diffusion models conditioned on agents' local histories share a unique fixed point corresponding to the global state, while in non-CO settings, shared fixed points yield a distribution of possible states given joint history. We further find that, with deep learning approximation errors, fixed points can deviate from true states and the deviation is negatively correlated to the Jacobian rank. Inspired by this low-rank property, we bound a deviation by constructing a surrogate linear regression model that approximates the local behavior of a diffusion model. With this bound, we propose a \emph{composite diffusion process} iterating over agents with theoretical convergence guarantees to the true state.

cs.LG↗

arXiv2024

Underwater Acoustic Signal Denoising Algorithms: A Survey of the State-of-the-art

This paper comprehensively reviews recent advances in underwater acoustic signal denoising, an area critical for improving the reliability and clarity of underwater communication and monitoring systems. Despite significant progress in the field, the complex nature of underwater environments poses unique challenges that complicate the denoising process. We begin by outlining the fundamental challenges associated with underwater acoustic signal processing, including signal attenuation, noise variability, and the impact of environmental factors. The review then systematically categorizes and discusses various denoising algorithms, such as conventional, decomposition-based, and learning-based techniques, highlighting their applications, advantages, and limitations. Evaluation metrics and experimental datasets are also reviewed. The paper concludes with a list of open questions and recommendations for future research directions, emphasizing the need for developing more robust denoising techniques that can adapt to the dynamic underwater acoustic environment.

cs.SD↗

arXiv2023

Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design

Multi-cellular robot design aims to create robots comprised of numerous cells that can be efficiently controlled to perform diverse tasks. Previous research has demonstrated the ability to generate robots for various tasks, but these approaches often optimize robots directly in the vast design space, resulting in robots with complicated morphologies that are hard to control. In response, this paper presents a novel coarse-to-fine method for designing multi-cellular robots. Initially, this strategy seeks optimal coarse-grained robots and progressively refines them. To mitigate the challenge of determining the precise refinement juncture during the coarse-to-fine transition, we introduce the Hyperbolic Embeddings for Robot Design (HERD) framework. HERD unifies robots of various granularity within a shared hyperbolic space and leverages a refined Cross-Entropy Method for optimization. This framework enables our method to autonomously identify areas of exploration in hyperbolic space and concentrate on regions demonstrating promise. Finally, the extensive empirical studies on various challenging tasks sourced from EvoGym show our approach's superior efficiency and generalization capability.

cs.AI↗

arXiv2023

Symmetry-Aware Robot Design with Structured Subgroups

Robot design aims at learning to create robots that can be easily controlled and perform tasks efficiently. Previous works on robot design have proven its ability to generate robots for various tasks. However, these works searched the robots directly from the vast design space and ignored common structures, resulting in abnormal robots and poor performance. To tackle this problem, we propose a Symmetry-Aware Robot Design (SARD) framework that exploits the structure of the design space by incorporating symmetry searching into the robot design process. Specifically, we represent symmetries with the subgroups of the dihedral group and search for the optimal symmetry in structured subgroups. Then robots are designed under the searched symmetry. In this way, SARD can design efficient symmetric robots while covering the original design space, which is theoretically analyzed. We further empirically evaluate SARD on various tasks, and the results show its superior efficiency and generalizability.

cs.AI↗

arXiv2022

Low-Rank Modular Reinforcement Learning via Muscle Synergy

Modular Reinforcement Learning (RL) decentralizes the control of multi-joint robots by learning policies for each actuator. Previous work on modular RL has proven its ability to control morphologically different agents with a shared actuator policy. However, with the increase in the Degree of Freedom (DoF) of robots, training a morphology-generalizable modular controller becomes exponentially difficult. Motivated by the way the human central nervous system controls numerous muscles, we propose a Synergy-Oriented LeARning (SOLAR) framework that exploits the redundant nature of DoF in robot control. Actuators are grouped into synergies by an unsupervised learning method, and a synergy action is learned to control multiple actuators in synchrony. In this way, we achieve a low-rank control at the synergy level. We extensively evaluate our method on a variety of robot morphologies, and the results show its superior efficiency and generalizability, especially on robots with a large DoF like Humanoids++ and UNIMALs.

cs.LG↗

arXiv2021

Birds of a Feather Flock Together: A Close Look at Cooperation Emergence via Multi-Agent RL

How cooperation emerges is a long-standing and interdisciplinary problem. Game-theoretical studies on social dilemmas reveal that altruistic incentives are critical to the emergence of cooperation but their analyses are limited to stateless games. For more realistic scenarios, multi-agent reinforcement learning has been used to study sequential social dilemmas (SSDs). Recent works show that learning to incentivize other agents can promote cooperation in SSDs. However, we find that, with these incentivizing mechanisms, the team cooperation level does not converge and regularly oscillates between cooperation and defection during learning. We show that a second-order social dilemma resulting from the incentive mechanisms is the main reason for such fragile cooperation. We formally analyze the dynamics of second-order social dilemmas and find that a typical tendency of humans, called homophily, provides a promising solution. We propose a novel learning framework to encourage homophilic incentives and show that it achieves stable cooperation in both SSDs of public goods and tragedy of the commons.

cs.MA↗

arXiv2020

Off-Policy Multi-Agent Decomposed Policy Gradients

Multi-agent policy gradient (MAPG) methods recently witness vigorous progress. However, there is a significant performance discrepancy between MAPG methods and state-of-the-art multi-agent value-based approaches. In this paper, we investigate causes that hinder the performance of MAPG algorithms and present a multi-agent decomposed policy gradient method (DOP). This method introduces the idea of value function decomposition into the multi-agent actor-critic framework. Based on this idea, DOP supports efficient off-policy learning and addresses the issue of centralized-decentralized mismatch and credit assignment in both discrete and continuous action spaces. We formally show that DOP critics have sufficient representational capability to guarantee convergence. In addition, empirical evaluations on the StarCraft II micromanagement benchmark and multi-agent particle environments demonstrate that DOP significantly outperforms both state-of-the-art value-based and policy-based multi-agent reinforcement learning algorithms. Demonstrative videos are available at https://sites.google.com/view/dop-mapg/.

cs.LG↗