Searcharxiv⌕ Search

arXiv subjects

Chao Gao

Publications and source records attributed to Chao Gao.

At least 19 recordsLinked to original sources
arXiv2026

NavArena: Automated Construction of Goal-Oriented Navigation Benchmarks from 3D Gaussian Splatting Reconstructions

Fixed 3D Gaussian Splatting (3DGS) reconstructions provide realistic novel views but lack the traversability constraints, valid goals, and closed-loop protocols required for navigation evaluation. We introduce NavArena, an automated framework that transforms fixed 3DGS reconstructions into benchmarks for goal-oriented visual navigation. NavArena integrates a frozen 3DGS model for egocentric RGB-D rendering, an occupancy costmap derived from Gaussian density and height statistics for reachability and collision queries, and semantic goal candidates lifted from multi-view open-vocabulary masks. These components support the automatic generation and unified closed-loop evaluation of goal-oriented navigation episodes. Across more than 2{,}000 scenes, NavArena generates 22.2 million expert trajectories. Spatial and semantic evaluations assess the derived navigation representations, while policy rollouts demonstrate the diagnostic value of the unified evaluation protocol. NavArena enables scalable and reproducible navigation evaluation on large-scale 3DGS reconstructions, and all benchmark-generation tools, evaluation protocols, and derived assets will be released publicly.

cs.RO↗
arXiv2026

StateSwap: Probing Support-Elimination Hidden States in Multiple-Choice Questions

Large language models often answer the same multiple-choice question inconsistently when it is posed under support-oriented and elimination-oriented framings. We investigate whether these discrepancies arise from different internal representations induced by the two framings. We introduce a dual-framing protocol with minimally varied prompts that use either support- or elimination-oriented framing while keeping the evaluation target fixed. To probe the internal computation, we append an untrained special token, [STATE], and treat its residual-stream activation as an intervention interface. Across both models, the two framings induce separable [STATE] activations concentrated in intermediate layers. Swapping these activations between paired prompts systematically changes predictions and improves cross-framing agreement, providing intervention-based evidence that the activations are behaviorally relevant. Beyond instance-level substitution, mean-difference steering directions derived from the dual-framing contrast exhibit more bounded layer-wise responses than matched contrastive activation addition directions under the evaluated protocol.

cs.CL↗
arXiv2026

WorldToken: Time-First Sequence Modeling for Robotic Imitation Learning

Robot policies receive heterogeneous observations at each decision step, yet sequence models differ in how they organize these inputs over time. We introduce WorldToken, a time-first policy instantiation that fuses multiview images, proprioception, and task conditioning within each policy timestep into one world token. A causal temporal Transformer models the resulting world-token sequence, and a diffusion action head generates action chunks. On 23 RoboCasa tasks, an 85.3M-parameter policy trained from scratch apart from a frozen pretrained CLIP text encoder achieves 59.45% mean closed-loop success using 2,900 generated demonstrations per task. A complete factorial sweep over five dataset sizes, five model sizes, and two training seeds shows consistent gains from additional target-domain data and diminishing returns beyond moderate model size. Under same-checkpoint history truncation, reducing visible history to one or two policy timesteps lowers closed-loop success for all 50 RoboCasa policies. On RMBench Blocks Ranking, reducing visible history from 146 to 8 seconds lowers evaluator success from 95% to 28%, while an exploratory extended rollout sustains the reference swap sequence for over 850 seconds. These results establish the empirical feasibility of the complete WorldToken instantiation and characterize its data-scaling and temporal-context behavior under the tested recipes. They do not establish superiority over alternative sequence organizations or isolate which components of the complete implementation drive the observed performance.

cs.RO↗
arXiv2026

DBLAST: Dependent Block Drafting for Stochastic Speculative Decoding

Speculative decoding accelerates large language models' inference by using a lightweight drafter to propose multiple future tokens and a target model to verify them. While recent block and diffusion-style drafters can predict several positions in a single pass, their training and sampling procedures are typically optimized for greedy decoding or assume that positions in the draft block are conditionally independent. This assumption becomes brittle in non-greedy speculative decoding, where the target distribution is deliberately stochastic and multiple continuations become plausible. We study this mismatch for block diffusion drafters and show that the accepted draft length degrades as the entropy of the target sampling distribution increases. We propose a dependent block drafter based on a low-rank latent mixture over token positions, complemented by an acceptance-oriented training objective that directly targets the expected verified length. Experiments with Qwen3-4B and Qwen3-8B on GSM8K, MT-Bench, HumanEval, and creative-writing benchmarks show that our approach, namely DBLast, consistently improves accepted length over independent block sampling, especially in higher-entropy decoding regimes.

cs.CL↗
arXiv2026

MOSAIK: Multi-Patch Content-Aware Spatial Allocation of Image Tokens for Efficient Generation

Pixel-space diffusion models avoid the reconstruction ceiling of latent diffusion models by generating directly in image space. However, their substantially higher token count makes generation expensive due to the quadratic complexity of self-attention. Several existing efficiency methods reduce this cost by using larger patches at selected denoising steps, thereby representing the image with fewer tokens. Yet, each step still uses a single patch size uniformly across the entire image, overlooking that different regions suffer different fidelity losses when coarsened. We introduce MOSAIK, a damage-guided framework that varies patch size across regions and denoising steps. MOSAIK adapts the PixelDiT backbone to generate arbitrary heterogeneous patch layouts, and a lightweight predictor uses intermediate denoising features to estimate the fidelity loss caused by coarsening each region. Given a token budget, our damage-guided layout predictor assigns fine patches to sensitive regions and coarse patches elsewhere. Remarkably, while reducing FLOPs by 70% and token count by 83%, MOSAIK matches the full-compute PixelDiT on GenEval and its DPG-Bench score drops by only 1.0 point. Compared to diverse efficiency paradigms, including temporal patch scheduling and feature caching, our approach delivers highly competitive performance at moderate budgets and consistently outperforms these baselines in highly constrained compute regimes.

cs.CV↗
arXiv2026

PL-LIT: A LiDAR-Inertial-Thermal SLAM Using Point-Line Features and Thermographic Mapping

Thermal imaging is resilient to adverse conditions, such as intense illumination, low-light operation, and fog, and can therefore mitigate odometry degradation when visible-spectrum imagery becomes unreliable. Nevertheless, most thermal cameras employ automatic gain control (AGC), and thermal images often present low global contrast despite containing informative edge structures. These characteristics undermine brightness constancy and cause conventional optical flow tracking-based odometry pipelines that fundamentally rely on the brightness constancy assumption across consecutive frames. To address these issues, we propose a general LiDAR-Inertial-Thermal SLAM system that accommodates both visible-light and thermal cameras. PL-LIT combines an online photometric calibration module with a deep neural network for point-line feature extraction, enabling more stable and repeatable thermal tracking. For state estimation, we design a tightly coupled LiDAR-Inertial-Thermal formulation within an Error-State Iterated Kalman Filter (ESIKF). We further introduce a line-feature constraint scheme ensuring the reliability of geometric constraints across varying thermal appearances. In addition, PL-LIT builds a probabilistic thermal-intensity voxel map, which supports real-time thermal anomaly detection. Extensive experiments demonstrate that PL-LIT exhibits generality and robustness in visible-light environments, achieves state-of-the-art performance on long-range thermal infrared datasets, and provides practical safety inspection functionality based on thermographic mapping.

cs.RO↗
arXiv2026

Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning

Reinforcement learning (RL) has become central to LLM post-training, yet the methods that dominate current pipelines, PPO and GRPO, represent only a narrow slice of what RL offers. Understanding why these methods prevail, and what alternatives exist, requires a principled examination of the design decisions that underlie any RL algorithm. This survey organizes that examination around three stages of algorithm construction. We begin with MDP creation: how the reward function, state space, action space, termination condition, and discount factor are, or could be, defined for LLM training. We then turn to exploration, covering temperature sampling, entropy regularization, intrinsic motivation, tree search, and curriculum learning. Finally, we address learning along four classical RL dimensions: model-free versus model-based, value-based versus policy-based versus actor-critic, on-policy versus off-policy, and credit assignment, including both Monte Carlo methods, which rely on full return estimates, and bootstrapping methods, which update estimates using other learned predictions. Mapping the LLM literature onto this taxonomy reveals a strikingly non-uniform distribution of research effort. Critic-free policy gradients and Monte Carlo credit assignment are densely populated, while value-based methods, off-policy actor-critic training, and bootstrapping-based credit assignment remain largely unexplored despite well-established counterparts in classical RL. These gaps represent concrete opportunities for transferring proven RL techniques to LLM training. By making these gaps explicit alongside the methods that have proven effective, this survey offers researchers in both RL and LLMs a shared framework for understanding current practice and identifying promising directions for future work.

cs.LG↗
arXiv2026

Covariance-Regulated Recursive Koopman Learning for Nonlinear Systems with Uncertain Time-Varying Dynamics

Offline models for autonomous robots often fail under time-varying dynamics outside their training distribution. Koopman operator theory offers a linear representation of nonlinear dynamics via lifting, but its transition to real-time recursive estimation may suffer numerical vulnerabilities: covariance windup under low excitation when using exponential forgetting, and vanishing gain without forgetting. This paper introduces a Covariance-Regulated Recursive Koopman Learning (CR-RKL) framework with two complementary strategies--error dead-zone gating and constant-trace normalization--each independently capable of preventing covariance explosion and parameter freezing, with the latter additionally preserving the geometric structure of uncertainty. Validated on a non-holonomic differential-drive robot with wheel slip and Stribeck friction and on a 26-gram butterfly-inspired flapping-wing micro aerial vehicle, CR-RKL achieves numerically stable and accurate online modeling, and when embedded in model predictive control, it maintains reliable tracking performance under uncertain, time-varying dynamics.

cs.RO↗
arXiv2026

AirDreamer: Generalist Drone Navigation with World Models

Navigating a drone in unseen and cluttered environments requires reliable generalization to unseen scene layouts and understanding of environmental structure relative to the robot's capabilities. Previous methods, which assume the same environment configuration, often rely heavily on human-designed perception pipelines and predefined rules to guide the robot toward the target. This process is environment-dependent and generalizes poorly across environments. Inspired by animal navigation behavior, we design a navigation framework that navigates with a reinforcement-learning-based policy on top of a world-model-based environment understanding to overcome these issues. In addition, a sparse reward function without hand-crafted shaping terms is designed to avoid local minima traps and encourage yaw control behaviors. In simulation and on real drones, our method exhibits emergent capabilities for navigating complex, unseen environments and escaping local optima where other methods fail. In challenging maps, it achieves a 5.3% higher navigation success rate than best baseline. Furthermore, the proposed framework achieves effective sim-to-real transfer without any tuning during deployment. The code will be publicly available.

cs.RO↗
arXiv2026

Neuromorphic Control of a Flapping-Wing Robot on Resource-Constrained Hardware

Flapping-Wing Micro Aerial Vehicles (FWMAVs) provide exceptional maneuverability and aerodynamic efficiency but pose significant challenges for onboard control due to nonlinear dynamics and stringent Size, Weight, and Power (SWaP) constraints, as exemplified by a butterfly-inspired robot less than 30 gram. To this end, we present a hierarchical neuromorphic control framework that enables fully onboard, closed-loop flight on a widely available, resource-constrained ESP32 microcontroller with a unit cost of approximately $5. Specifically, our method deploys two lightweight Spiking Neural Networks (SNNs) onboard: one for state estimation from raw sensory feedback and another for control via modulation of a Central Pattern Generator (CPG) for wing actuation. Trained by imitation learning, the system achieves stable pitch and heading angle tracking during untethered real-world flight. Experimental results further reveal that the SNN-based controller reduces latency by 36% (1059us to 680us) and power by 18% (0.033W to 0.027W) for inference compared to the conventional Artificial Neural Network (ANN) baseline, demonstrating the viability of spike-based computation without specialized hardware. To the best of our knowledge, this work constitutes the first demonstration of fully onboard neuromorphic control for autonomous flight of a FWMAV, highlighting the potential of SNNs to enable energy-efficient autonomy under stringent SWaP constraints. Visual abstract: http://bit.ly/4nI8ECY Code: https://anonymous.4open.science/r/Espikify-76E3/

cs.RO↗
arXiv2026

NORM-Nav: Zero-Shot Mobile Robot Navigation with Natural Language Behavioral Constraints

Mobile robots operating in human-centered environments must generate not only collision-free paths but also trajectories that follow local behavioral conventions. Conventional costmap-based navigation emphasizes geometric feasibility and often overlooks such requirements, which can result in socially inappropriate behaviors. This paper presents NORM-Nav, a zero-shot framework that integrates natural language behavioral constraints into costmap-based planning. An LLM parses each instruction into structured constraints and grounds them using real-time vision--LiDAR perception. These constraints are encoded as multi-layer costmaps that represent geometric, semantic, directional, and velocity cues and are directly compatible with standard grid-based planners. Simulation and real-world experiments indicate that NORM-Nav improves task success rates and produces trajectories closer to human references than representative baselines. The project website is available at https://ei-nav.github.io/NORM-Nav.

cs.RO↗
arXiv2026

On the Impossibility of Specification Testing of Interference Models Based on Exposure Mappings

Researchers use interference models based on exposure mappings to facilitate estimation of causal effects in randomized experiments with interference. To test the veracity of such models, researchers can use specification tests that aim to detect departures from the stipulated model. However, existing tests suffer from poor power and are often unable to detect important model violations. The main result in this paper is to show that the specification testing problem for exposure mapping models is inherently difficult, and the poor power of existing tests is inescapable. In particular, the worst-case Type I and Type II error rates must sum to one for any specification test of such models, ruling out the existence of a uniformly consistent test. This is the worst-case overall error rate achieved by a naive test that discards all data and arbitrarily rejects the null at random; the testing problem is in this sense impossible. This negative result holds true for all exposure mappings, all sample sizes, for uniformly bounded outcomes, and for alternatives that are maximally separated from the null. While some tests can detect some type of departures from the null model, there will always be relevant departures from the null that are undetectable. Informative specification tests must therefore restrict the alternative model against which they seek to attain power for, beyond the restrictions imposed by the exposure mappings alone. We illustrate this by providing a uniformly consistent test for differentiating no-interference from a network-linear-in-means model.

math.ST↗
arXiv2026

High-Dimensional Statistics: Reflections on Progress and Open Problems

Over the past two decades, the field of high-dimensional statistics has experienced substantial progress, driven largely by technological advances that have dramatically reduced the cost and effort for data collection and storage across a broad range of domains, including biology, medicine, astronomy, and the social and environmental sciences. Modern datasets are increasingly complex, often exhibiting rich dependency, heterogeneity, and other features that challenge traditional statistical methods. In response, high-dimensional statistics has evolved to address more sophisticated estimation and inference problems. This evolution has, in turn, fostered deep connections with and contributions to a wide range of research areas, including optimization, concentration of measure, random matrix theory, information theory, and theoretical computer science. Given the rapid pace of recent developments in high-dimensional statistics, our goal is to synthesize representative advances, highlight common themes and open problems, and point to important works that offer entry points into the field.

math.ST↗
arXiv2026

Adaptive Confidence Intervals in Efron's Gaussian Two-Groups Model

Robust uncertainty quantification is increasingly important in modern data analysis and is often formalized under Huber's model, which allows an $\varepsilon$-fraction of arbitrary corruptions. In many experimental sciences, however, the measurement protocol is well controlled, and contamination is more plausibly introduced upstream. Motivated by this noise-oblivious nature of adversaries, we study confidence intervals for the null location parameter $\theta$ in Efron's Gaussian two-groups model, where an unknown fraction $\varepsilon$ of observations have arbitrarily shifted means, but all samples share the same law of additive Gaussian measurement noise with variance $\sigma^2$. We characterize the minimax-optimal length among confidence intervals with a prescribed coverage level uniformly over the unknown contamination proportion and all noise-oblivious adversaries. Although prior work has shown that the minimax point estimation rate of theta does not deteriorate when $\varepsilon$ becomes unknown, our results reveal that, with a given $\sigma^2$, the minimax-optimal length of confidence intervals that are adaptive to unknown $\varepsilon$ is of order $\sigma (n^{-1/4}+\varepsilon^{1/2}/\max\{1, \log(en \varepsilon^2)\}^{1/2})$, which is polynomially worse than the optimal length when $\varepsilon$ is known. When the variance $\sigma^2$ is also unknown, we show a further degradation: no adaptive confidence interval can be shorter than $\Omega(\sigma n^{-1/8})$. Algorithmically, we introduce a Fourier-based certification procedure built on Carath\'{e}odory's positive-semidefiniteness constraints. By scanning candidate points and accepting those whose residual characteristic function is certifiably consistent with a Gaussian location mixture, our algorithm attains the minimax lower bound in the known-variance setting and is computable in polynomial time.

math.ST↗
arXiv2026

STRIDE-ED: A Strategy-Grounded Stepwise Reasoning Framework for Empathetic Dialogue Systems

Empathetic dialogue requires not only recognizing a user's emotional state but also making strategy-aware, context-sensitive decisions throughout response generation. However, the lack of a comprehensive empathy strategy framework, explicit task-aligned multi-stage reasoning, and high-quality strategy-aware data fundamentally limits existing approaches, preventing them from effectively modeling empathetic dialogue as a complex, multi-stage cognitive and decision-making process. To address these challenges, we propose STRIDE-ED, a STRategy-grounded, Interpretable, and DEep reasoning framework that models Empathetic Dialogue through structured, strategy-conditioned reasoning. To support effective learning, we develop a strategy-aware data refinement pipeline integrating LLM-based annotation, multi-model consistency-weighted evaluation, and dynamic sampling to construct high-quality training data aligned with empathetic strategies. Furthermore, we adopt a two-stage training paradigm that combines supervised fine-tuning with multi-objective reinforcement learning to better align model behaviors with target emotions, empathetic strategies, and response formats. Extensive experiments demonstrate that STRIDE-ED generalizes across diverse open-source LLMs and consistently outperforms existing methods on both automatic metrics and human evaluations. Our data and code are publicly available at https://github.com/jicoder-nwpu/STRIDE-ED.

cs.CL↗
arXiv2026

Robust Regression with Adaptive Contamination in Response: Optimal Rates and Computational Barriers

We study robust regression under a contamination model in which covariates are clean while the responses may be corrupted in an adaptive manner. Unlike the classical Huber's contamination model, where both covariates and responses may be contaminated and consistent estimation is impossible when the contamination proportion is a non-vanishing constant, it turns out that the clean-covariate setting admits strictly improved statistical guarantees. Specifically, we show that the additional information in the clean covariates can be carefully exploited to construct an estimator that achieves a better estimation rate than that attainable under Huber contamination. In contrast to the Huber model, this improved rate implies consistency even when the contamination is a constant. A matching minimax lower bound is established using Fano's inequality together with the construction of contamination processes that match $m> 2$ distributions simultaneously, extending the previous two-point lower bound argument in Huber's setting. Despite the improvement over the Huber model from an information-theoretic perspective, we provide formal evidence -- in the form of Statistical Query and Low-Degree Polynomial lower bounds -- that the problem exhibits strong information-computation gaps. Our results strongly suggest that the information-theoretic improvements cannot be achieved by polynomial-time algorithms, revealing a fundamental gap between information-theoretic and computational limits in robust regression with clean covariates.

math.ST↗
arXiv2026

Implementation of non-local arbitrary two-qubit controlled gates via geometric quantum computation with Rydberg anti-blockade

In the context of Rydberg anti-blockade, this paper proposes a new scheme for a high-fidelity controlled-unitary gate based on non-adiabatic holonomic quantum computation. Under specific detuning and interaction conditions, the scheme achieves a suitable evolution path for non-adiabatic holonomic quantum computation through reverse engineering of pulse parameters. Numerical simulations show that the geometric gate maintains high fidelity even in the presence of spontaneous radiation and laser intensity errors. Finally,we extend our designed quantum gates to non-local gates and investigate their use in converting four-qubit entangled states. This finding indicates the potential applicability of our scheme to complex quantum information processing tasks.

quant-ph↗
arXiv2026

Modeling Trend Dynamics with Variational Neural ODEs for Information Popularity Prediction

Predicting the future popularity of information in online social networks is a crucial yet challenging task, due to the complex spatiotemporal dynamics underlying information diffusion. Existing methods typically use structural or sequential patterns within the observation window as direct inputs for subsequent popularity prediction. However, most approaches lack the ability to explicitly model the overall trend of popularity up to the prediction time, which leads to limited predictive capability. To address these limitations, we propose VNOIP, a novel method based on variational neural Ordinary Differential Equations (ODEs) for information popularity prediction. Specifically, VNOIP introduces bidirectional jump ODEs with attention mechanisms to capture long-range dependencies and bidirectional context within cascade sequences. Furthermore, by jointly considering both cascade patterns and overall trend temporal patterns, VNOIP explicitly models the continuous-time dynamics of popularity trend trajectories with variational neural ODEs. Additionally, a knowledge distillation loss is employed to align the evolution of prior and posterior latent variables. Extensive experiments on real-world datasets demonstrate that VNOIP is highly competitive in both prediction accuracy and efficiency compared to state-of-the-art baselines.

cs.SI↗