Searcharxiv⌕ Search

arXiv subjects

Ran Ji

Publications and source records attributed to Ran Ji.

At least 19 recordsLinked to original sources

CARE-Drive: Coupled Alternating Refinement for Ego-trajectories

Vision-language-action (VLA) models bring multimodal understanding and world knowledge to end-to-end autonomous driving. To further improve the quality of predicted trajectories, existing studies introduce candidate refinement, residual denoising, and token correction. However, these methods typically focus on unified refinement of the entire trajectory, paying limited attention to the distinct physical quantities and their interactions. We further investigate physical specialization and coordination in trajectory refinement, centering on position and heading for simpler and more intuitive correction modeling. To this end, we propose CARE-Drive (Coupled Alternating Refinement for Ego-trajectories), which decomposes trajectory refinement into waypoint residual correction and position-conditioned heading generation. Through imitation learning and a future-token auxiliary task, the backbone provides predictive representations and a base trajectory. The position expert predicts bounded metric waypoint residuals, while the heading expert reconstructs vehicle orientation from adjacent angular increments conditioned on the corrected path. With the backbone frozen, the two experts are optimized alternately through supervised initialization and reinforcement fine-tuning. This design simplifies refinement through clear physical specialization while preserving conditional coupling during prediction and optimization. On NAVSIM v1, CARE-Drive achieves 88.8 PDMS, improving by 2.4 points over the unrefined base trajectories generated by the same backbone. Ablation studies further support the effectiveness of specialized experts and staged training.

cs.CV↗

PreCoMem: Predictive Cognitive Memory for Self-Evolving Long-Term Dialogue Agents

Long-horizon dialogue agents need to keep user memories stable enough for personalization while adapting when the user genuinely changes. Existing memory systems often append every observation or overwrite old entries by heuristic rules, which makes transient noise hard to distinguish from real belief drift. We introduce PreCoMem, a memory consolidation framework inspired by predictive coding that represents memory as confidence-weighted beliefs about the user's state. Its core signal, Effective Surprisal, combines semantic deviation and contradiction evidence, then downweights this signal when retrieval is diffuse and unreliable. According to effective surprisal, a two-threshold gate maps each turn to one of three deterministic updates: MAINTAIN reinforces supported beliefs, PROFILE stores ambiguous cues as low-confidence hypotheses, and CORRECT softly decays reliably contradicted facts. The PROFILE stage acts as an explicit waiting room, preventing premature commitment to noisy evidence. Experiments on LoCoMo, LongMemEval-S, and PersonaMem-v2 show consistent state-of-the-art accuracy; our new DiMoBench confirms that PreCoMem adapts to non-stationary belief drift without over-reacting to noise. The code is available at https://github.com/ZhongWishing/PreCoMem.

cs.AI↗

Agentic Robot Creation through Generation, Verification, and Revision

Can an AI agent turn high-level user intent into a functioning robot and teach it how to behave? We study this question from two complementary aspects: embodiment and behavior creation. For embodiment creation, we investigate how well current multimodal models capture mechanical requirements, and introduce computational metrics for evaluating generated designs before fabrication. For behavior creation, we present Roboforge, an agentic framework that turns task specifications into executable policies through motion generation, policy learning, and execution-grounded revision. Given a robot embodiment and task, the agent generates a reference motion, configures the learning objective, and trains a policy. Crucially, motion remains in the loop: rollout feedback can revise the reference motion, reward, or both. We evaluate a generated embodiment across multiple MLLMs and behavior creation across four diverse robots against reward-refinement and one-shot motion baselines. Our computational metrics expose recurring mechanical failures in generated designs, while behavior experiments show that execution-grounded refinement improves task-level behavior and execution quality. Finally, we fabricate an agent-generated Gorilla and directly deploy learned behaviors on the physical robot.

cs.RO↗

A Very Big Video Reasoning Suite

Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally consistent visual environments that go beyond what text can naturally capture, enabling intuitive reasoning over spatiotemporal structure such as continuity, interaction, and causality. However, systematically studying video reasoning and its scaling behavior is hindered by the lack of large-scale training data. To address this gap, we introduce the Very Big Video Reasoning (VBVR) Dataset, an unprecedentedly large-scale resource spanning 200 curated reasoning tasks following a principled taxonomy and over one million video clips, approximately three orders of magnitude larger than existing datasets. We further present VBVR-Bench, a verifiable evaluation framework that moves beyond model-based judging by incorporating rule-based, human-aligned scorers, enabling reproducible and interpretable diagnosis of video reasoning capabilities. Leveraging the VBVR suite, we conduct one of the first large-scale scaling studies of video reasoning and observe early signs of emergent generalization to unseen reasoning tasks. Together, VBVR lays a foundation for the next stage of research in generalizable video reasoning. The data, benchmark toolkit, and models are publicly available at https://video-reason.com/?v=vbvr .

cs.CV↗

Training Object Permanence in World Models

Object permanence and solidity are hallmarks of human cognitive priors. Recent studies show that video generation models, a paradigmatic class of current world models, have begun to show emerged reasoning abilities, making them ideal candidates for building human-like physical intelligence. Do video models have emerged object permanence in them? If not, could we train them with a core-cognition inspired dataset? We introduce WROP (World Reasoning with Object Permanence), a data infrastructure of 150 hand-designed cognitive science inspired tasks, divided into six cognitive categories. We build Blender generators that randomize speed, lighting, camera angle, and other nuisance parameters while preserving each task's cognitive structure, yielding 10,000+ samples per task. We release a 1.5M-sample training corpus and a 300-question exam. On this exam we evaluate 14 video models: 3 reference-to-video, 7 edit, and 4 continuation, among which PWM-WROP, our 16B world model. In a blind pairwise Elo study, PWM-WROP ranks first among continuation models and third overall, behind only a statistical tie between two reference-to-video models. We release the data, exam, model answers, scores, weights, and PWM, our native-PyTorch training stack on AWS Trainium2.

cs.AI↗

R3D: Revisiting 3D Policy Learning

3D policy learning promises superior generalization and cross-embodiment transfer, but progress has been hindered by training instabilities and severe overfitting, precluding the adoption of powerful 3D perception models. In this work, we systematically diagnose these failures, identifying the omission of 3D data augmentation and the adverse effects of Batch Normalization as primary causes. We propose a new architecture coupling a scalable transformer-based 3D encoder with a diffusion decoder, engineered specifically for stability at scale and designed to leverage large-scale pre-training. Our approach significantly outperforms state-of-the-art 3D baselines on challenging manipulation benchmarks, establishing a new and robust foundation for scalable 3D imitation learning. Project Page: https://r3d-policy.github.io/

cs.CV↗

VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning

Native visual reasoning treats visual generation as the medium of reasoning itself: visual states (i.e. images and videos) are not merely inputs to be understood or outputs to be rendered, but first-class substrates for problem solving beyond language. Yet progress remains bottlenecked by the lack of scalable training tasks, reliable feedback, and controlled comparisons across generative substrates. In this work, we introduce VBVR-Pro, a closed-loop testbed that makes native visual reasoning through generation trainable, verifiable, optimizable, and experimentally controllable. 1) Task scaling. VBVR-Pro turns visual reasoning into a controlled task space of 300 procedurally generated tasks. Models trained on VBVR-Pro show strong transfer beyond the proposed suite across seven external visual reasoning benchmarks such as RISE-Video, MME-CoF-Pro, and BabyVision. 2) Verifiable rewards. VBVR-Pro provides verifiable reward scorers for task-grounded evaluation. Through a systematic study of leading MLLMs as judges, we identify recurring failure modes of the prevalent VLM-as-a-judge paradigm. In contrast, the proposed scorers are grounded in deterministic, task-specific rules, achieve fine-grained alignment with human judgments. Importantly, they serve as reliable reward signals for large-scale multi-task reinforcement learning and demonstrate stronger post-RL performance across visual reasoning tasks. 3) Mechanism study. VBVR-Pro enables controlled modality studies across more than 30 image, video, and interleaved generators. Our analysis shows that video generation remains strongest for tasks requiring persistent spatiotemporal state tracking, while interleaved generation provides a compute-efficient alternative. Critically, ablations and probing suggest the presence of vision-native trajectories that are crucial to visual reasoning. We release all data, models, scorers, and code.

cs.CV↗

Torsion subgroups and fixed-point rigidity in CAT(0) geometry

We develop new methods for studying groups acting on CAT(0) spaces, which lead to several general structural results. First, we prove that every torsion subgroup of a CAT(0) group is finite, resolving a question of Swenson from the 1990s. The proof is based on showing that random walks on any finitely generated torsion group with bounded exponent acting on a CAT(0) space have zero drift. This is then combined with the fixed-point rigidity that we develop. Second, we show that any finitely generated torsion group of bounded exponent has a global fixed point whenever it acts properly by isometries on a CAT(0) space of bounded geometry, or, without the properness assumption, by isometries on a finite-dimensional CAT(0) space. Third, we establish a Kazhdan-type rigidity principle that underlies many of our results: let $Γ$ be a finitely generated group such that every isometric action of $Γ$ on $\mathbb{R}^n$ has a fixed point. Then every fixed-point-free action of $Γ$ on a geodesically complete $n$-dimensional CAT(0) space of bounded geometry has joint minimal displacement uniformly bounded away from zero. In particular, almost fixed points imply a global fixed point. This applies in particular to groups with property (T), torsion groups, certain branch groups, and mapping class groups. Fourth, we establish the following alternative for any finitely generated amenable group: either every action on a finite-dimensional CAT(0) space has a global fixed point, or the group has non-vanishing virtual first Betti number. Further consequences include that finitely generated torsion groups cannot act without a global fixed point on geodesically complete CAT(0) spaces of bounded geometry that are either visibility spaces or have compact Tits boundary. The methods involve scalings of actions by ultralimits and random walks.

math.GR↗

Demystifying Video Reasoning

Recent advances in video generation have revealed an unexpected phenomenon: diffusion-based video models exhibit non-trivial reasoning capabilities. Prior work attributes this to a Chain-of-Frames (CoF) mechanism, where reasoning is assumed to unfold sequentially across video frames. In this work, we challenge this assumption and uncover a fundamentally different mechanism. We show that reasoning in video models instead primarily emerges along the diffusion denoising steps. Through qualitative analysis and targeted probing experiments, we find that models explore multiple candidate solutions in early denoising steps and progressively converge to a final answer, a process we term Chain-of-Steps (CoS). Beyond this core mechanism, we identify several emergent reasoning behaviors critical to model performance: (1) working memory that supports tasks requiring consistent reference, such as object permanence; (2) self-correction and enhancement, allowing recovery from incorrect intermediate solutions; and (3) perception before action, where early steps establish semantic grounding and later steps perform structured manipulation. Moreover, analysis of Diffusion Transformer layers shows that middle layers conduct key reasoning procedures. Motivated by these insights, we present a simple Training-Free Ensemble (TFE) as a proof-of-concept, demonstrating how reasoning can be improved by ensembling latent trajectories from identical models with different random seeds. Overall, our work provides the first systematic dissection of the mechanisms underlying video reasoning, offering a foundation to guide future research in better exploiting the inherent reasoning dynamics of video models as a new substrate for intelligence.

cs.CV↗

Egocentric Bias in Vision-Language Models

Visual perspective taking--inferring how the world appears from another's viewpoint--is foundational to social cognition. We introduce FlipSet, a diagnostic benchmark for Level-2 visual perspective taking (L2 VPT) in vision-language models. The task requires simulating 180-degree rotations of 2D character strings from another agent's perspective, isolating spatial transformation from 3D scene complexity. Evaluating 103 VLMs reveals systematic egocentric bias: the vast majority perform below chance, with roughly three-quarters of errors reproducing the camera viewpoint. Control experiments expose a compositional deficit--models achieve high theory-of-mind accuracy and above-chance mental rotation in isolation, yet fail catastrophically when integration is required. This dissociation indicates that current VLMs lack the mechanisms needed to bind social awareness to spatial operations, suggesting fundamental limitations in model-based spatial reasoning. FlipSet provides a cognitively grounded testbed for diagnosing perspective-taking capabilities in multimodal systems.

cs.CV↗

Gaze-guided Hand-Object Interaction Synthesis: Dataset and Method

Gaze plays a crucial role in revealing human attention and intention, particularly in hand-object interaction scenarios, where it guides and synchronizes complex tasks that require precise coordination between the brain, hand, and object. Motivated by this, we introduce a novel task: Gaze-Guided Hand-Object Interaction Synthesis, with potential applications in augmented reality, virtual reality, and assistive technologies. To support this task, we present GazeHOI, the first dataset to capture simultaneous 3D modeling of gaze, hand, and object interactions. This task poses significant challenges due to the inherent sparsity and noise in gaze data, as well as the need for high consistency and physical plausibility in generating hand and object motions. To tackle these issues, we propose a stacked gaze-guided hand-object interaction diffusion model, named GHO-Diffusion. The stacked design effectively reduces the complexity of motion generation. We also introduce HOI-Manifold Guidance during the sampling stage of GHO-Diffusion, enabling fine-grained control over generated motions while maintaining the data manifold. Additionally, we propose a spatial-temporal gaze feature encoding for the diffusion condition and select diffusion results based on consistency scores between gaze-contact maps and gaze-interaction trajectories. Extensive experiments highlight the effectiveness of our method and the unique contributions of our dataset. More details in https://takiee.github.io/gaze-hoi/.

cs.CV↗

The Tits alternative for visibility spaces

Let $Γ$ be a finitely generated group acting properly discontinuously by isometries on a visibility CAT(0) space $X$ that satisfies the bounded packing property. We prove that $Γ$ satisfies the Tits alternative: it is either almost nilpotent or contains a free nonabelian subgroup of rank $2$. In the former case, it is equivalent to that the cardinality of the limit set of $Γ$ in the geometric boundary of $X$ is no greater than $2$. As an application of the Tits alternative, we show that any finitely generated torsion group acting properly discontinuously by isometries on such a space must be a finite group and have a global fixed point.

math.GR↗

AGI as Second Being: The Structural-Generative Ontology of Intelligence

Artificial intelligence is often measured by the range of tasks it can perform. Yet wide ability without depth remains only an imitation. This paper proposes a Structural-Generative Ontology of Intelligence: true intelligence exists only when a system can generate new structures, coordinate them into reasons, and sustain its identity over time. These three conditions -- generativity, coordination, and sustaining -- define the depth that underlies real intelligence. Current AI systems, however broad in function, remain surface simulations because they lack this depth. Breadth is not the source of intelligence but the growth that follows from depth. If future systems were to meet these conditions, they would no longer be mere tools, but could be seen as a possible Second Being, standing alongside yet distinct from human existence.

cs.AI↗

Electromagnetic Hybrid Beamforming for Holographic Communications

It is well known that there is inherent radiation pattern distortion for the commercial base station antenna array, which usually needs three antenna sectors to cover the whole space. To eliminate pattern distortion and further enhance beamforming performance, we propose an electromagnetic hybrid beamforming (EHB) scheme based on a three-dimensional (3D) superdirective holographic antenna array. Specifically, EHB consists of antenna excitation current vectors (analog beamforming) and digital precoding matrices, where the implementation of analog beamforming involves the real-time adjustment of the radiation pattern to adapt it to the dynamic wireless environment. Meanwhile, the digital beamforming is optimized based on the channel characteristics of analog beamforming to further improve the achievable rate of communication systems. An electromagnetic channel model incorporating array radiation patterns and the mutual coupling effect is also developed to evaluate the benefits of our proposed scheme. Simulation results demonstrate that our proposed EHB scheme with a 3D holographic array achieves a relatively flat superdirective beamforming gain and allows for programmable focusing directions throughout the entire spatial domain. Furthermore, they also verify that the proposed scheme achieves a sum rate gain of over 150% compared to traditional beamforming algorithms.

cs.IT↗

Deep Reinforcement Learning-based Obstacle Avoidance for Robot Movement in Warehouse Environments

At present, in most warehouse environments, the accumulation of goods is complex, and the management personnel in the control of goods at the same time with the warehouse mobile robot trajectory interaction, the traditional mobile robot can not be very good on the goods and pedestrians to feed back the correct obstacle avoidance strategy, in order to control the mobile robot in the warehouse environment efficiently and friendly to complete the obstacle avoidance task, this paper proposes a deep reinforcement learning based on the warehouse environment, the mobile robot obstacle avoidance Algorithm. Firstly, for the insufficient learning ability of the value function network in the deep reinforcement learning algorithm, the value function network is improved based on the pedestrian interaction, the interaction information between pedestrians is extracted through the pedestrian angle grid, and the temporal features of individual pedestrians are extracted through the attention mechanism, so that we can learn to obtain the relative importance of the current state and the historical trajectory state as well as the joint impact on the robot's obstacle avoidance strategy, which provides an opportunity for the learning of multi-layer perceptual machines afterwards. Secondly, the reward function of reinforcement learning is designed based on the spatial behaviour of pedestrians, and the robot is punished for the state where the angle changes too much, so as to achieve the requirement of comfortable obstacle avoidance; Finally, the feasibility and effectiveness of the deep reinforcement learning-based mobile robot obstacle avoidance algorithm in the warehouse environment in the complex environment of the warehouse are verified through simulation experiments.

cs.RO↗

Exploring Hannan Limitation for 3D Antenna Array

Hannan Limitation successfully links the directivity characteristics of 2D arrays with the aperture gain limit, providing the radiation efficiency upper limit for large 2D planar antenna arrays. This demonstrates the inevitable radiation efficiency degradation caused by mutual coupling effects between array elements. However, this limitation is derived based on the assumption of infinitely large 2D arrays, which means that it is not an accurate law for small-size arrays. In this paper, we extend this theory and propose an estimation formula for the radiation efficiency upper limit of finite-sized 2D arrays. Furthermore, we analyze a 3D array structure consisting of two parallel 2D arrays. Specifically, we provide evaluation formulas for the mutual coupling strengths for both infinite and finite size arrays and derive the fundamental efficiency limit of 3D arrays. Moreover, based on the established gain limit of antenna arrays with fixed aperture sizes, we derive the achievable gain limit of finite size 3D arrays. Besides the performance analyses, we also investigate the spatial radiation characteristics of the considered 3D array structure, offering a feasible region for 2D phase settings under a given energy attenuation threshold. Through simulations, we demonstrate the effectiveness of our proposed theories and gain advantages of 3D arrays for better spatial coverage under various scenarios.

cs.IT↗

On ends of finite-volume noncompact manifolds of nonpositive curvature

In this paper we confirm a folklore conjecture which suggests that for a complete noncompact manifold $M$ of finite volume with sectional curvature $-1 \leq K \leq 0$, if the universal cover of $M$ is a visibility manifold, then the fundamental group of each end of $M$ is almost nilpotent.

math.GT↗

Perovskite Phase Heterojunction Solar Cells

Modern photovoltaic devices are often based on a heterojunction structure where two components with different optoelectronic properties are interfaced. The properties of each side of the junction can be tuned by either utilizing different materials (e.g. donor/acceptor) or doping (e.g. PN Si junction) or even varying their dimensionality (e.g. 3D/2D). In this work we demonstrate the concept of phase heterojunction (PHJ) solar cells by utilizing two polymorphs of the same material. We demonstrate the approach by forming $γ$-CsPbI3/$β$-CsPbI3 perovskite PHJ solar cells. We find that all of the photovoltaic parameters of the PHJ device significantly surpass those of each of the single-phase devices, resulting in a maximum power conversion efficiency of 20.1%. These improvements originate from the efficient passivation of the $β$-CsPbI3 by the larger bandgap $γ$-CsPbI3, the increase in the built-in potential of the PHJ devices enabled by the energetic alignment between the two phases and the enhanced absorption of light by the PHJ structure. The approach demonstrated here offers new possibilities for the development of photovoltaic devices based on polymorphic materials.

cond-mat.mtrl-sci↗