Hao Sun

Xiaoyu Zhan, Wenxuan Huang, Hao Sun et al.

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved 2D visual understanding, prompting interest in their application to complex 3D reasoning tasks. However, it remains unclear whether these models can effectively capture the detailed spatial information required for robust real-world performance, especially cross-view consistency, a key requirement for accurate 3D reasoning. Considering this issue, we introduce Viewpoint Learning, a task designed to evaluate and improve the spatial reasoning capabilities of MLLMs. We present the Viewpoint-100K dataset, consisting of 100K object-centric image pairs with diverse viewpoints and corresponding question-answer pairs. Our approach employs a two-stage fine-tuning strategy: first, foundational knowledge is injected to the baseline MLLM via Supervised Fine-Tuning (SFT) on Viewpoint-100K, resulting in significant improvements across multiple tasks; second, generalization is enhanced through Reinforcement Learning using the Group Relative Policy Optimization (GRPO) algorithm on a broader set of questions. Additionally, we introduce a hybrid cold-start initialization method designed to simultaneously learn viewpoint representations and maintain coherent reasoning thinking. Experimental results show that our approach significantly activates the spatial reasoning ability of MLLM, improving performance on both in-domain and out-of-domain reasoning tasks. Our findings highlight the value of developing foundational spatial skills in MLLMs, supporting future progress in robotics, autonomous systems, and 3D scene understanding.

Hao Sun

The prevailing approach to aligning Large Language Models (LLMs) typically relies on human or AI feedback and assumes access to specific types of preference datasets. In our work, we question the efficacy of such datasets and explore various scenarios where alignment with expert demonstrations proves more realistic. We build a sequential decision-making framework to formulate the problem of aligning LLMs using demonstration datasets. Drawing insights from inverse reinforcement learning and imitation learning, we introduce various approaches for divergence minimization in the LLM alignment tasks. Our analysis highlights the mass-covering and mode-seeking behaviors of these different approaches. Inclusively, we examine the pros and cons of the classical supervised fine-tuning method, elaborating on scenarios where different methods shine.

Hao Sun, Rundong He, Zhongyi Han et al.

Few-shot OOD detection focuses on recognizing out-of-distribution (OOD) images that belong to classes unseen during training, with the use of only a small number of labeled in-distribution (ID) images. Up to now, a mainstream strategy is based on large-scale vision-language models, such as CLIP. However, these methods overlook a crucial issue: the lack of reliable OOD supervision information, which can lead to biased boundaries between in-distribution (ID) and OOD. To tackle this problem, we propose CLIP-driven Outliers Synthesis~(CLIP-OS). Firstly, CLIP-OS enhances patch-level features' perception by newly proposed patch uniform convolution, and adaptively obtains the proportion of ID-relevant information by employing CLIP-surgery-discrepancy, thus achieving separation between ID-relevant and ID-irrelevant. Next, CLIP-OS synthesizes reliable OOD data by mixing up ID-relevant features from different classes to provide OOD supervision information. Afterward, CLIP-OS leverages synthetic OOD samples by unknown-aware prompt learning to enhance the separability of ID and OOD. Extensive experiments across multiple benchmarks demonstrate that CLIP-OS achieves superior few-shot OOD detection capability.