Yichen Li

Yichen Li, Kaichun Mo, Yueqi Duan et al.

Shape assembly composes complex shapes geometries by arranging simple part geometries and has wide applications in autonomous robotic assembly and CAD modeling. Existing works focus on geometry reasoning and neglect the actual physical assembly process of matching and fitting joints, which are the contact surfaces connecting different parts. In this paper, we consider contacting joints for the task of multi-part assembly. A successful joint-optimized assembly needs to satisfy the bilateral objectives of shape structure and joint alignment. We propose a hierarchical graph learning approach composed of two levels of graph representation learning. The part graph takes part geometries as input to build the desired shape structure. The joint-level graph uses part joints information and focuses on matching and aligning joints. The two kinds of information are combined to achieve the bilateral objectives. Extensive experiments demonstrate that our method outperforms previous methods, achieving better shape structure and higher joint alignment accuracy.

Yunsheng Tian, Karl D. D. Willis, Bassel Al Omari et al.

The automated assembly of complex products requires a system that can automatically plan a physically feasible sequence of actions for assembling many parts together. In this paper, we present ASAP, a physics-based planning approach for automatically generating such a sequence for general-shaped assemblies. ASAP accounts for gravity to design a sequence where each sub-assembly is physically stable with a limited number of parts being held and a support surface. We apply efficient tree search algorithms to reduce the combinatorial complexity of determining such an assembly sequence. The search can be guided by either geometric heuristics or graph neural networks trained on data with simulation labels. Finally, we show the superior performance of ASAP at generating physically realistic assembly sequence plans on a large dataset of hundreds of complex product assemblies. We further demonstrate the applicability of ASAP on both simulation and real-world robotic setups. Project website: asap.csail.mit.edu

Xiaotang Gai, Jiaxiang Liu, Yichen Li et al.

Medical Visual Question Answering (Med-VQA) holds significant potential for clinical decision support, yet existing efforts primarily focus on 2D imaging with limited task diversity. This paper presents 3D-RAD, a large-scale dataset designed to advance 3D Med-VQA using radiology CT scans. The 3D-RAD dataset encompasses six diverse VQA tasks: anomaly detection, image observation, medical computation, existence detection, static temporal diagnosis, and longitudinal temporal diagnosis. It supports both open- and closed-ended questions while introducing complex reasoning challenges, including computational tasks and multi-stage temporal analysis, to enable comprehensive benchmarking. Extensive evaluations demonstrate that existing vision-language models (VLMs), especially medical VLMs exhibit limited generalization, particularly in multi-temporal tasks, underscoring the challenges of real-world 3D diagnostic reasoning. To drive future advancements, we release a high-quality training set 3D-RAD-T of 136,195 expert-aligned samples, showing that fine-tuning on this dataset could significantly enhance model performance. Our dataset and code, aiming to catalyze multimodal medical AI research and establish a robust foundation for 3D medical visual understanding, are publicly available at https://github.com/Tang-xiaoxiao/3D-RAD.

Xinlin Zhuang, Feilong Tang, Haolin Yang et al.

Supervised Fine-Tuning (SFT) plays a pivotal role in adapting Large Language Models (LLMs) to specialized domains such as medical reasoning. However, existing SFT practices often rely on unfiltered datasets that contain redundant and low-quality samples, leading to substantial computational costs and suboptimal performance. Although existing methods attempt to alleviate this problem by selecting data based on sample difficulty, defined by knowledge and reasoning complexity, they overlook each sample's optimization utility reflected in its gradient. Interestingly, we find that gradient-based influence alone favors easy-to-optimize samples that cause large parameter shifts but lack deep reasoning chains, while difficulty alone selects noisy or overly complex cases that fail to guide stable optimization. Based on this observation, we propose a data selection strategy, Difficulty-Influence Quadrant (DIQ), which prioritizes samples in the high-difficulty-high-influence quadrant to balance complex clinical reasoning with substantial gradient influence, enabling efficient medical reasoning with minimal fine-tuning data. Furthermore, Human and LLM-as-a-judge evaluations show that DIQ-selected subsets demonstrate higher data quality and generate clinical reasoning that is more aligned with expert practices in differential diagnosis, safety check, and evidence citation, as DIQ emphasizes samples that foster expert-like reasoning patterns. Extensive experiments on medical reasoning benchmarks demonstrate that DIQ enables models fine-tuned on only 1% of selected data to match full-dataset performance, while using 10% consistently outperforms baseline methods, highlighting the superiority of principled data selection over brute-force scaling. The code and data are available at https://github.com/mihara-bot/DIQ.

Yi-Chen Li, Tian Xu, Yang Yu et al.

The alignment of Large Language Models (LLMs) is critically dependent on reward models trained on costly human preference data. While recent work explores bypassing this cost with AI feedback, these methods often lack a rigorous theoretical foundation. In this paper, we discover that a powerful generalist reward model is already latently present within any LLM trained via standard next-token prediction. We prove that this endogenous reward is not a heuristic, but is theoretically equivalent to a reward function learned through offline inverse reinforcement learning. This connection allows us to directly elicit a high-quality reward signal from a base (pre-trained or supervised fine-tuned) model without any further training. Critically, we also prove that subsequent reinforcement learning using this endogenous reward leads to a policy with a provably superior error bound compared to the base model. To our best knowledge, this is the first theoretical proof of the effectiveness of reinforcement learning for LLMs. Our experiments validate this theory, demonstrating that our method not only outperforms existing LLM-as-a-judge approaches but can also surpass explicitly trained reward models. These findings suggest that the reward modeling stage can be replaced by a principled method of eliciting the knowledge already captured during pre-training, heralding a more efficient, powerful, and scalable paradigm for LLMs alignment as well as multi-modal models.

Xiwei Liu, Yulong Li, Yichen Li et al.

Language-guided supervision, which utilizes a frozen semantic target from a Pretrained Language Model (PLM), has emerged as a promising paradigm for visual Continual Learning (CL). However, relying on a single target introduces two critical limitations: 1) semantic ambiguity, where a polysemous category name results in conflicting visual representations, and 2) intra-class visual diversity, where a single prototype fails to capture the rich variety of visual appearances within a class. To this end, we propose MuproCL, a novel framework that replaces the single target with multiple, context-aware prototypes. Specifically, we employ a lightweight LLM agent to perform category disambiguation and visual-modal expansion to generate a robust set of semantic prototypes. A LogSumExp aggregation mechanism allows the vision model to adaptively align with the most relevant prototype for a given image. Extensive experiments across various CL baselines demonstrate that MuproCL consistently enhances performance and robustness, establishing a more effective path for language-guided continual learning.

Jinsong Yang, Zeyuan Hu, Yichen Li

Underwater fish detection (UFD) remains a challenging task in computer vision due to low object resolution, significant background interference, and high visual similarity between targets and surroundings. Existing approaches primarily focus on local feature enhancement or incorporate complex attention mechanisms to highlight small objects, often at the cost of increased model complexity and reduced efficiency. To address these limitations, we propose an efficient path aggregation network (EPANet), which leverages complementary feature integration to achieve accurate and lightweight UFD. EPANet consists of two key components: an efficient path aggregation feature pyramid network (EPA-FPN) and a multi-scale diverse-division short path bottleneck (MS-DDSP bottleneck). The EPA-FPN introduces long-range skip connections across disparate scales to improve semantic-spatial complementarity, while cross-layer fusion paths are adopted to enhance feature integration efficiency. The MS-DDSP bottleneck extends the conventional bottleneck structure by introducing finer-grained feature division and diverse convolutional operations, thereby increasing local feature diversity and representation capacity. Extensive experiments on benchmark UFD datasets demonstrate that EPANet outperforms state-of-the-art methods in terms of detection accuracy and inference speed, while maintaining comparable or even lower parameter complexity.