arXiv subjects

Chang Luo

Publications and source records attributed to Chang Luo.

6 recordsLinked to original sources

arXiv2026

TV-Regulated OPD: Direction Matters in On-Policy Distillation

On-Policy Distillation (OPD) facilitates the transfer of knowledge from domain expert to student in the post-training phase of Large Language Models (LLMs). However, the supervision signals in mainstream OPD methods suffer from high variance and noise which is generally instable during training. In this work, we systematically investigated what really matters to the performance and the fundamental mechanisms behind the instability during training. We found that retaining only the sign of token-level advantages is sufficient to achieve the performance comparable to standard OPD. Meanwhile, smoother and bounded advantages can stabilize the training process without sacrificing its performance. These motivated us to shape the advantages using the Total Variation (TV) and propose a robust TV regulated On-Policy Distillation (TV-OPD) method. Benefiting from the bounded and diminished advantages, TV-OPD exhibits stable training dynamics and steady late-stage performance. We conducted comprehensive experiments and found that, across various settings, TV-OPD consistently achieved better performance and lower variance in the late-stage of training.

cs.LG↗

arXiv2026

CT2Yarn: Yarn-Level Reconstruction of Crochet from Computed Tomography

We introduce CT2Yarn, a human-in-the-loop framework for recovering a single continuous yarn path from micro-computed tomography (micro-CT) scans of real crochet objects. Crochet is a craft that creates complex three-dimensional shapes by interlocking loops formed from a single yarn. Recovering the underlying yarn path from external observations is challenging because of severe self-occlusion. While micro-CT reveals the full internal structure of a crochet object, the volumetric scan alone does not explicitly encode how the yarn traverses the object. This challenge stems from the hierarchical structure of yarn: a yarn consists of multiple twisted plies, and each ply itself consists of twisted fibers. Consequently, local fiber orientations observed in micro-CT scans are not aligned with the overall yarn direction. To recover yarn-level orientations from ply-level fiber orientations, we first estimate local fiber directions using Gabor filtering and convert the volume into an oriented point cloud. We then introduce an anisotropic mean-shift procedure that aggregates local fiber orientations within a neighborhood of the yarn radius into yarn-level orientation estimates. Combined with an automatic topology skeletonization strategy, our method extracts yarn-path fragments. Subsequent fragment linking, junction cleaning, and loop detection merge these trees into a small number of long curves. Where the automatic reconstruction remains ambiguous, a sketch-based user interface enables users to interactively complete the single continuous yarn path. The recovered yarn path enables downstream applications including physically based simulation, ply-level rendering, and stitch-pattern extraction.

cs.GR↗

arXiv2026

BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation

Hallucinations remain a major obstacle to deploying large language models (LLMs) in knowledge-intensive settings, where generated responses must be faithfully grounded in provided evidence. Reinforcement learning (RL) is a promising direction for hallucination mitigation, but response-level faithfulness rewards suffer from a granularity mismatch: localized hallucinations can cause supported content to receive spurious penalties. Although recent work introduces fine-grained feedback such as claim-level verification and token-level rewards, unbalanced credit assignment can still induce length, verbosity, or optimization-noise biases. We propose BALTO, a Balanced Token-level Policy Optimization framework for hallucination mitigation. BALTO extracts checkable factual claims, verifies them against the reference context, and projects claim-level judgments to token-level labels. A balanced token-level credit assignment mechanism is introduced into the framework. This design redistributes probability mass from unsupported content toward faithful content, rather than suppressing the entire response. We systematically analyze the limitations of response-level rewards from a theoretical standpoint, and prove BALTO's advantages in training stability and optimization efficiency for hallucination mitigation. Experiments on ConFiQA, RAGTruth, and FinLLM-Eval show that BALTO achieves the highest faithfulness across all six model--benchmark settings and consistently outperforms existing post-training baselines in Q-Score, demonstrating a stronger faithfulness--informativeness trade-off.

cs.CL↗

arXiv2026

LeafFit: Plant Assets Creation from 3D Gaussian Splatting

We propose LeafFit, a pipeline that converts 3D Gaussian Splatting (3DGS) of individual plants into editable, instanced mesh assets. While 3DGS faithfully captures complex foliage, its high memory footprint and lack of mesh topology make it incompatible with traditional game production workflows. We address this by leveraging the repetition of leaf shapes; our method segments leaves from the unstructured 3DGS, with optional user interaction included as a fallback. A representative leaf group is selected and converted into a thin, sharp mesh to serve as a template; this template is then fitted to all other leaves via differentiable Moving Least Squares (MLS) deformation. At runtime, the deformation is evaluated efficiently on-the-fly using a vertex shader to minimize storage requirements. Experiments demonstrate that LeafFit achieves higher segmentation quality and deformation accuracy than recent baselines while significantly reducing data size and enabling parameter-level editing.

cs.GR↗

arXiv2024

Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking

We introduce Motion2VecSets, a 4D diffusion model for dynamic surface reconstruction from point cloud sequences. While existing state-of-the-art methods have demonstrated success in reconstructing non-rigid objects using neural field representations, conventional feed-forward networks encounter challenges with ambiguous observations from noisy, partial, or sparse point clouds. To address these challenges, we introduce a diffusion model that explicitly learns the shape and motion distribution of non-rigid objects through an iterative denoising process of compressed latent representations. The diffusion-based priors enable more plausible and probabilistic reconstructions when handling ambiguous inputs. We parameterize 4D dynamics with latent sets instead of using global latent codes. This novel 4D representation allows us to learn local shape and deformation patterns, leading to more accurate non-linear motion capture and significantly improving generalizability to unseen motions and identities. For more temporally-coherent object tracking, we synchronously denoise deformation latent sets and exchange information across multiple frames. To avoid computational overhead, we designed an interleaved space and time attention block to alternately aggregate deformation latents along spatial and temporal domains. Extensive comparisons against state-of-the-art methods demonstrate the superiority of our Motion2VecSets in 4D reconstruction from various imperfect observations. More detailed information can be found at https://vveicao.github.io/projects/Motion2VecSets/.

cs.CV↗

arXiv2020

WHU-Hi: UAV-borne hyperspectral with high spatial resolution (H2) benchmark datasets for hyperspectral image classification

Classification is an important aspect of hyperspectral images processing and application. At present, the researchers mostly use the classic airborne hyperspectral imagery as the benchmark dataset. However, existing datasets suffer from three bottlenecks: (1) low spatial resolution; (2) low labeled pixels proportion; (3) low degree of subclasses distinction. In this paper, a new benchmark dataset named the Wuhan UAV-borne hyperspectral image (WHU-Hi) dataset was built for hyperspectral image classification. The WHU-Hi dataset with a high spectral resolution (nm level) and a very high spatial resolution (cm level), which we refer to here as H2 imager. Besides, the WHU-Hi dataset has a higher pixel labeling ratio and finer subclasses. Some start-of-art hyperspectral image classification methods benchmarked the WHU-Hi dataset, and the experimental results show that WHU-Hi is a challenging dataset. We hope WHU-Hi dataset can become a strong benchmark to accelerate future research.

eess.IV↗