19 papers
SpikeOcc: Towards Resilient Multimodal 3D Occupancy Perception via Spiking Experts
Yiding Sun, Zijie Xu, Hongqiang Lin +7
Multimodal 3D occupancy prediction underpins safe autonomous driving through comprehensive scene understanding. However, existing methods have largely pursued higher accuracy throu…
VICT: Verifier-Instrumented Credit Tracing for Long-Horizon LLM Agent Reinforcement Learning
Pengcheng Li, Zhengyang Zhang, Dongxu Zhang +2
Fine-grained credit assignment is a central challenge in reinforcement learning for long horizon LLM agents. Standard objectives often train from programmatically verifiable termin…
SpikingMOT: A Spike-Driven Multi-Object Tracker
Yiding Sun, Xiangyang Yang, Dongxu Zhang +7
Multi-object tracking (MOT) plays a fundamental role in visual perception, where accurate trajectory prediction is essential for reliable target association under complex motion pa…
Better Starts, Better Ends: Bootstrapped Iterative Self-Reasoning Distillation for Compressed Reasoning
Leichao Dong, Dongxu Zhang, Yiding Sun +4
Large reasoning models often solve problems through long chain-of-thought (CoT) traces, yet much of this computation is spent on redundant derivations, repeated self-verification,…
SPARK: Susceptibility-Guided Profiling and Steering of Latent Reasoning States in Large Language Models
Dongxu Zhang, Yiding Sun, Zihao Guo +5
Reasoning failures in large language models (LLMs) are usually evaluated from final answers, but a wrong answer does not reveal why the model failed. The same incorrect output may…
GaussFusion: Towards Multimodal 3D Gaussian Pretraining
Zhixuan You, Jihua Zhu, Yiding Sun +5
3D Gaussian Splatting provides an explicit representation that jointly models geometry and appearance, serving as a scalable foundation for 3D representation learning. Existing pre…
SeeMe: Mitigating Hallucinations in Large Vision-Language Models through Effective Visual Token Engineering
Kai Tang, Jinhao You, Bohua Zhang +6
Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual understanding tasks such as image captioning and visual question answering. However, they remain su…
Tri-Efficient Transfer Learning for Point Cloud Videos
Yiding Sun, Dongxu Zhang, Jihua Zhu +6
While point cloud foundation models have significantly advanced point cloud video understanding, existing parameter-efficient fine-tuning (PEFT) methods still suffer from two criti…
Offline Policy Optimization with Posterior Sampling
Hongqiang Lin, Dongxu Zhang, Yiding Sun +3
A fundamental challenge in model-based offline reinforcement learning (RL) lies in the trade-off between generalization and robustness against exploitation errors in out-of-distrib…
CFMS: A Coarse-to-Fine Multimodal Synthesis Framework for Enhanced Tabular Reasoning
Qixian Huang, Hongqiang Lin, Tong Fu +5
Reasoning over tabular data is a crucial capability for tasks like question answering and fact verification, as it requires models to comprehend both free-form questions and semi-s…
PointRFT: Explicit Reinforcement Fine-tuning for Point Cloud Few-shot Learning
Yankai Wang, Yiding Sun, Qirui Wang +3
Understanding spatial dynamics and semantics in point cloud is fundamental for comprehensive 3D comprehension. While reinforcement learning algorithms such as Group Relative Policy…
PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inference
Qirui Wang, Qi Guo, Yiding Sun +4
Personalized text-to-image generation lets users fine-tune diffusion models into repositories of concept-specific checkpoints, but serving these repositories efficiently is difficu…
CMHANet: A Cross-Modal Hybrid Attention Network for Point Cloud Registration
Dongxu Zhang, Yingsen Wang, Yiding Sun +3
Robust point cloud registration is a fundamental task in 3D computer vision and geometric deep learning, essential for applications such as large-scale 3D reconstruction, augmented…
IGASA: Integrated Geometry-Aware and Skip-Attention Modules for Enhanced Point Cloud Registration
Dongxu Zhang, Jihua Zhu, Shiqi Li +4
Point cloud registration (PCR) is a fundamental task in 3D vision and provides essential support for applications such as autonomous driving, robotics, and environmental modeling.…
Not All Queries Need Deep Thought: CoFiCot for Adaptive Coarse-to-fine Stateful Refinement
Dongxu Zhang, Hongqiang Lin, Yiding Sun +4
Scaling test-time computation enhances LLM reasoning ability but faces a uniform computation paradox. Allocating identical resources leads to over-correction on simple tasks and in…
Robust Regularized Policy Iteration under Transition Uncertainty
Hongqiang Lin, Zhenghui Fu, Weihao Tang +4
Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift. The lea…
PointCoT: A Multi-modal Benchmark for Explicit 3D Geometric Reasoning
Dongxu Zhang, Yiding Sun, Pengcheng Li +12
While Multimodal Large Language Models (MLLMs) demonstrate proficiency in 2D scenes, extending their perceptual intelligence to 3D point cloud understanding remains a significant c…
Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring
Dongxu Zhang, Yiding Sun, Cheng Tan +4
While Chain-of-Thought (CoT) reasoning significantly enhances the performance of Multimodal Large Language Models (MLLMs), its autoregressive nature incurs prohibitive latency cons…
Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning
Dongxu Zhang, Yujun Wu, Yiding Sun +5
While Chain-of-Thought (CoT) prompting empowers Large Language Models (LLMs), ensuring reasoning reliability remains an open challenge. Contrary to the prevailing cascading failure…