Author

Dong-Xu Zhang

h-index 8 View on Semantic Scholar

We have 6 of 24 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Partition-Invariant Tuning for 3D Scene Understanding

Scene-level point cloud understanding remains challenging due to diverse geometries and spatial layouts. While pre-trained 3D point cloud foundation models (PFMs) offer strong transferability, full fine-tuning (FFT) incurs substantial computational and storage costs. Parameter-efficient fine-tuning (PEFT) provides a pr...

Hong-Qiang Lin, Tian-Le Wang, Shui-Wang Li et al. · 0 citations

Preprint Jul 2026

SpikingMOT: A Spike-Driven Multi-Object Tracker

SpikingMOT is proposed as a spike-driven tracker that adaptively models sparse trajectory dynamics with spiking neural networks (SNNs) and brings SNNs into MOT, opening a promising direction for efficient tracking.

Yiding Sun, Xiangyang Yang, Dongxu Zhang et al. · 1 citation

Jul 2026

SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models

SPARK is introduced, which uses hidden-state response to diagnose whether a model internally enters an effective reasoning state and to guide lightweight test-time steering, and suggests that susceptibility can serve not only as a diagnostic signal for reasoning failures, but also as a practical guide for targeted test...

Dongxu Zhang, Yiding Sun, Zihao Guo et al. · arXiv.org · 0 citations

#artificial intelligence Preprint Aug 2026

VICT: Verifier-Instrumented Credit Tracing for Long-Horizon LLM Agent Reinforcement Learning

VICT (VerifierInstrumented Credit Tracing), a training-time interface that exposes executable or evidence backed atoms and traces them back to actions through dependency-valid proof edges, improves substantially over outcome-only training and achieves strong performance alongside recent fine-grained credit methods.

Peng-Cheng Li, Zhengyang Zhang, Dong-Xu Zhang et al. · 0 citations

Jul 2026

Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning

BIRD(Bootstrapped Iterative Self-Reasoning Distillation), a two-stage self-reasoning distillation method that improves the rollout distribution before on-policy training and achieves a stronger accuracy-efficiency trade-off than prompting and cold-start on-policy distillation on MATH-500 and AIME benchmarks.

Leichao Dong, Dong-Xu Zhang, Yi-Ding Sun et al. · arXiv.org · 0 citations

Preprint Jul 2026

SeeMe: Mitigating Hallucinations in Large Vision-Language Models through Effective Visual Token Engineering

SeeMe is proposed, a training-free framework that introduces the concept of feature engineering from traditional machine learning into LVLMs and restructures visual tokens through a three-stage token engineering process to suppress hallucination sources while preserving informative visual evidence.

Kai Tang, Jinhao You, Bohua Zhang et al. · 2 citations