← Search

Zhiyuan Yang

20 accepted papers

2026

Circular-DPO: Aligning Multi-Stage 3D Generative Models via Preference Feedback Loop

CVPR 2026

Multi-stage generative models have shown great promise in 3D content creation due to focused generation of structure or texture in different stages, but their outputs often fail to align with human preferences. The key bottleneck to apply alignment methods is the presence of non-differentiable opera

Cited by 0SourceScholar
2026

Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling

ICLR 2026poster

Test-time scaling has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs) by allocating additional computational resources during inference. However, this paradigm is inherently inefficient due to the generation of redundant and repetitive reasonin…

Cited by 0SourcecodeScholar
2026

TrimR: Verifier-based Training-Free Thinking Trimming for Efficient Test-Time Scaling

ICLR 2026poster

Large Reasoning Models (LRMs) demonstrate exceptional capability in tackling complex mathematical, logical, and coding tasks by leveraging extended Chain-of-Thought (CoT) reasoning. Test-time scaling methods—such as prolonging CoT with explicit token-level exploration—can push LRMs’ accuracy boundar…

Cited by 0SourceScholar
2025

Distribution Backtracking Builds A Faster Convergence Trajectory for Diffusion Distillation

ICLR 2025poster

Accelerating the sampling speed of diffusion models remains a significant challenge. Recent score distillation methods distill a heavy teacher model into a student generator to achieve one-step generation, which is optimized by calculating the difference between two score functions on the samples ge…

2025

Exploring the Interpretability of EEG-Inception Convolutional Neural Networks for Epilepsy Prediction

ICASSP 2025accepted

Predicting epileptic seizures effectively allows patients to take preventive measures in advance, reducing accident risk and enhancing safety. Several modeling challenges remain open: (1) The complex spatiotemporal dependency of EEG signals makes it challenging to design a model that efficiently ext…

Cited by 0SourceScholar
2025

Generalization of Humanoid Arm Manipulation Based on Keypoints Synergetic Guidance

RA-L 2025

In humanoid robot manipulation imitation learning, arm and tool synergies are required to accomplish tasks. However, the existence of arm and tool shape variations within the demonstrators and between the demonstrator-robot impacts the generalization performance. This paper models the arm and tool a

Cited by 0SourceScholar
2025

HFD-Teacher: High-Frequency Depth Distillation from Depth Foundation Models for Enhanced Depth Completion

ICCV 2025poster

Depth completion, the task of reconstructing dense depth maps from sparse depth and RGB images, plays a critical role in 3D scene understanding. However, existing methods often struggle to recover high-frequency details, such as regions with fine structures or weak signals, since depth sensors may f…

Cited by 0SourcePDFScholar
2025

ZBOT: A Novel Modular Robot Capable of Active Transformation from Snake to Bipedal Configuration through RL

IROS 2025

In recent years, significant progress has been made in the prototype design and control methodologies of modular snake robots. However, there is still relatively little research on the potential enabled by the active morphological transformation of robots. This paper presents a novel modular snake r

Cited by 0SourceScholar
2024

Design of a Multi-Environmentally Adaptable Modular Self-Reconfigurable Robot

RA-L 2024

Modular self-reconfigurable robots (MSRRs) have significantly progressed in hardware and algorithm development. However, they are generally used in terrestrial environments, leaving broad scenarios to be explored and benefited. This letter presents a novel amphibious self-reconfigurable robot (ASRR)

Cited by 11SourceScholar
2024

Empowering and Assessing the Utility of Large Language Models in Crop Science

NeurIPS 2024poster

Large language models (LLMs) have demonstrated remarkable efficacy across knowledge-intensive tasks. Nevertheless, their untapped potential in crop science presents an opportunity for advancement. To narrow this gap, we introduce CROP, which includes a novel instruction tuning dataset specifically d…

Cited by 1SourcePDFScholar
2024

GAM-Depth: Self-Supervised Indoor Depth Estimation Leveraging a Gradient-Aware Mask and Semantic Constraints

ICRA 2024poster

Self-supervised depth estimation has evolved into an image reconstruction task that minimizes a photometric loss. While recent methods have made strides in indoor depth estimation, they often produce inconsistent depth estimation in textureless areas and unsatisfactory depth discrepancies at object…

Cited by 3SourcecodeScholar
2024

Reducing Spatial Fitting Error in Distillation of Denoising Diffusion Models

AAAI 2024technical

Denoising Diffusion models have exhibited remarkable capabilities in image generation. However, generating high-quality samples requires a large number of iterations. Knowledge distillation for diffusion models is an effective method to address this limitation with a shortened sampling process but c…

2024

Semi-Autonomous Grasping Control of Prosthetic Hand and Wrist Based on Motion Prior Field

RA-L 2024

Grasping multiple affordance parts and from arbitrary directions for complex shaped objects still remains a challenging problem for prosthetic hand with wrist. We propose a semi-autonomous control method that uses only an integrated in-hand camera to predict the final grasping part on an object as t

Cited by 7SourceScholar
2024

Smooth Tchebycheff Scalarization for Multi-Objective Optimization

ICML 2024poster

Multi-objective optimization problems can be found in many real-world applications, where the objectives often conflict each other and cannot be optimized by a single solution. In the past few decades, numerous methods have been proposed to find Pareto solutions that represent optimal trade-offs amo…

2022

Feature Augmentation Learning for Few-Shot Palmprint Image Recognition With Unconstrained Acquisition

ICASSP 2022accepted

Few-shot learning is challenging in unconstrained palmprint recognition, where the palmprint images are collected by unconstrained acquisitions, i.e., different imaging sensors, backgrounds, palm postures, and illumination conditions. Furthermore, due to the lack of unconstrained palmprint databases…

Cited by 0SourceScholar
2022

Pareto Set Learning for Expensive Multi-Objective Optimization

NeurIPS 2022accept

Expensive multi-objective optimization problems can be found in many real-world applications, where their objective function evaluations involve expensive computations or physical experiments. It is desirable to obtain an approximate Pareto front with a limited evaluation budget. Multi-objective Bay…

2022

Pareto Set Learning for Neural Multi-Objective Combinatorial Optimization

ICLR 2022poster

Multiobjective combinatorial optimization (MOCO) problems can be found in many real-world applications. However, exactly solving these problems would be very challenging, particularly when they are NP-hard. Many handcrafted heuristic methods have been proposed to tackle different MOCO problems over…