arXiv subjects

Chao Zhan

Publications and source records attributed to Chao Zhan.

6 recordsLinked to original sources

arXiv2026

Reasoning to Regulate: Chain-of-Thought for Traffic Rule Understanding

Understanding and complying with traffic regulations is a safety-critical requirement for autonomous driving, yet remains challenging due to the diversity and context dependence of traffic signage. Importantly, regulation understanding is not a simple recognition task, but a reasoning problem: whether a rule applies depends on interpreting the sign in relation to the spatial layout of lanes and scene context. To support such reasoning, MapDR provide fine-grained annotations that link each traffic sign's regulatory rules to the specific lanes they govern. Existing methods, however, largely treat this as direct sequence prediction, ignoring the underlying reasoning that connects sign semantics and map structure. To address this limitation, we explicitly incorporate reasoning into this task and propose a framework that equips vision-language models (VLMs) with chain-of-thought (CoT) capabilities. We first design a scalable CoT curation pipeline that bootstraps rationales from a strong LLM through a two-round strategy and employs a VLM-based verifier to filter out incorrect cases, yielding a high-quality set of (CoT, answer) pairs. Building on this foundation, we adopt a two-stage training scheme: supervised fine-tuning (SFT) to teach rationale-to-answer generation, followed by GRPO reinforcement learning with answer-grounded, fine-grained rewards to further improve final answer accuracy. Extensive experiments on MapDR show that our approach significantly improves both interpretability and accuracy, establishing the first reasoning-based framework for regulation-aware autonomous driving.

cs.CV↗

arXiv2026

Ascend-RaBitQ: Heterogeneous NPU-CPU Acceleration of Billion-Scale Similarity Search with 1-bit Quantization

Vector similarity search is a critical component of modern AI systems, but traditional CPU-based implementations face fundamental scalability bottlenecks for billion-scale corpora due to prohibitive computational overhead and memory bandwidth limitations. While Neural Processing Units (NPUs) offer orders-of-magnitude higher compute density, existing CPU/GPU-optimized 1-bit RaBitQ quantization implementations cannot be directly ported to NPU architectures due to fundamental hardware mismatches, and homogeneous design paradigms struggle to simultaneously balance accuracy, memory footprint, and performance. This paper presents Ascend-RaBitQ, the first heterogeneous NPU-CPU optimized IVF-RaBitQ system for billion-scale vector search, built on the core insight that decoupling coarse ranking (NPU) from fine ranking (CPU) allows each stage to leverage its optimal hardware, breaking the long-standing accuracy-memory-performance trade-off. We propose a three-stage heterogeneous execution path comprising AI Core-accelerated coarse ranking on 1-bit quantized vectors, on-device AI CPU Top-k processing, and host CPU fine re-ranking on full-precision vectors. We introduce four NPU architecture-native optimizations: fused AIC-AIV operators for parallel distance computation, computation flow restructuring to exploit rotation orthogonality, fine-grained index block-level load balancing that breaks query boundaries, and intra-NPU pipeline parallelism between AI Core and AI CPU to mask Top-k latency. Evaluation on standard datasets shows that Ascend-RaBitQ achieves 3.0X to 62.8X faster index construction than the CPU baseline, up to 11.7X throughput improvement over the fastest CPU IVF-RaBitQ implementation, and over two orders of magnitude over the mathematically equivalent CPU baseline, while demonstrating encouraging scalability on distributed multi-NPU systems.

cs.IR↗

arXiv2025

Data-Driven Reconstruction of Significant Wave Heights from Sparse Observations

Reconstructing high-resolution regional significant wave height fields from sparse and uneven buoy observations remains a core challenge for ocean monitoring and risk-aware operations. We introduce AUWave, a hybrid deep learning framework that fuses a station-wise sequence encoder (MLP) with a multi-scale U-Net enhanced by a bottleneck self-attention layer to recover 32$\times$32 regional SWH fields. A systematic Bayesian hyperparameter search with Optuna identifies the learning rate as the dominant driver of generalization, followed by the scheduler decay and the latent dimension. Using NDBC buoy observations and ERA5 reanalysis over the Hawaii region, AUWave attains a minimum validation loss of 0.043285 and a slightly right-skewed RMSE distribution. Spatial errors are lowest near observation sites and increase with distance, reflecting identifiability limits under sparse sampling. Sensitivity experiments show that AUWave consistently outperforms a representative baseline in data-richer configurations, while the baseline is only marginally competitive in the most underdetermined single-buoy cases. The architecture's multi-scale and attention components translate into accuracy gains when minimal but non-trivial spatial anchoring is available. Error maps and buoy ablations reveal key anchor stations whose removal disproportionately degrades performance, offering actionable guidance for network design. AUWave provides a scalable pathway for gap filling, high-resolution priors for data assimilation, and contingency reconstruction.

eess.SP↗

arXiv2025

Improving Significant Wave Height Prediction Using Chronos Models

Accurate wave height prediction is critical for maritime safety and coastal resilience, yet conventional physics-based models and traditional machine learning methods face challenges in computational efficiency and nonlinear dynamics modeling. This study introduces Chronos, the first implementation of a large language model (LLM)-powered temporal architecture (Chronos) optimized for wave forecasting. Through advanced temporal pattern recognition applied to historical wave data from three strategically chosen marine zones in the Northwest Pacific basin, our framework achieves multimodal improvements: (1) 14.3% reduction in training time with 2.5x faster inference speed compared to PatchTST baselines, achieving 0.575 mean absolute scaled error (MASE) units; (2) superior short-term forecasting (1-24h) across comprehensive metrics; (3) sustained predictive leadership in extended-range forecasts (1-120h); and (4) demonstrated zero-shot capability maintaining median performance (rank 4/12) against specialized operational models. This LLM-enhanced temporal modeling paradigm establishes a new standard in wave prediction, offering both computationally efficient solutions and a transferable framework for complex geophysical systems modeling.

cs.LG↗

arXiv2024

MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling

Real-time video dubbing that preserves identity consistency while achieving accurate lip synchronization remains a critical challenge. Existing approaches face a trilemma: diffusion-based methods achieve high visual fidelity but suffer from prohibitive computational costs, while GAN-based solutions sacrifice lip-sync accuracy or dental details for real-time performance. We present MuseTalk, a novel two-stage training framework that resolves this trade-off through latent space optimization and spatio-temporal data sampling strategy. Our key innovations include: (1) During the Facial Abstract Pretraining stage, we propose Informative Frame Sampling to temporally align reference-source pose pairs, eliminating redundant feature interference while preserving identity cues. (2) In the Lip-Sync Adversarial Finetuning stage, we employ Dynamic Margin Sampling to spatially select the most suitable lip-movement-promoting regions, balancing audio-visual synchronization and dental clarity. (3) MuseTalk establishes an effective audio-visual feature fusion framework in the latent space, delivering 30 FPS output at 256*256 resolution on an NVIDIA V100 GPU. Extensive experiments demonstrate that MuseTalk outperforms state-of-the-art methods in visual fidelity while achieving comparable lip-sync accuracy. %The codes and models will be made publicly available upon acceptance. The code is made available at \href{https://github.com/TMElyralab/MuseTalk}{https://github.com/TMElyralab/MuseTalk}

cs.CV↗

arXiv2021

The response of the Convolutional Neural Network to the transient noise in Gravitational wave detection

In recent years, much work have studied the use of convolutional neural networks for gravitational-wave detection. However little work pay attention to whether the transient noise can trigger the CNN model or not. In this paper, we study the responses of the sine-Gaussian glitches, the Gaussian glitches and the ring-down glitches in the trained convolutional neural network classifier. We find that the network is robust to the sine-Gaussian and Gaussian glitches, whose false alarm probabilities are close to that of the LIGO-like noises, in contrast to the case of the ring-down glitches, in which the false alarm probability is far larger than that of the LIGO-like noises. We also investigate the responses of the glitches with different frequency. We find that when the frequency of the glitches falls in that of the trained GW signals, the false alarm probability of the glitches will be much larger than that of the LIGO-like noises, and the probability of the glitches being misjudged as the GW signals may even exceed 30%.

gr-qc↗