RCPU: Rotation-Constrained Error Compensation for Structured Pruning of a Large Language Model

In this paper, we propose a rotation-constrained compensation method to address the errors introduced by structured pruning of large language models (LLMs). LLMs are trained on massive datasets and accumulate rich semantic knowledge in their representation space. In contrast, pruning is typically carried out with only a small amount of calibration data, which makes output mismatches unavoidable. Although direct least-squares fitting can reduce such errors, it tends to overfit to the limited calibration set, destructively modifying pretrained weights. To overcome this difficulty, we update the pruned parameters under a rotation constraint. This constrained update preserves the geometry of output representations (i.e., norms and inner products) and simultaneously re-aligns the pruned subspace with the original outputs. Furthermore, in rotation-constrained compensation, removing components that strongly contribute to the principal directions of the output makes error recovery difficult. Since input dimensions with large variance strongly affect these principal directions, we design a variance-aware importance score that ensures such dimensions are preferentially kept in the pruned model. By combining this scoring rule with rotation-constrained updates, the proposed method effectively compensates errors while retaining the components likely to be more important in a geometry-preserving manner. In the experiments, we apply the proposed method to LLaMA-7B and evaluate it on WikiText-2 and multiple language understanding benchmarks. The results demonstrate consistently better perplexity and task accuracy compared with existing baselines.

MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook

This paper reviews the MARS2 2025 Challenge on Multimodal Reasoning. We aim to bring together different approaches in multimodal machine learning and LLMs via a large benchmark. We hope it better allows researchers to follow the state-of-the-art in this very dynamic area. Meanwhile, a growing number of testbeds have boosted the evolution of general-purpose large language models. Thus, this year's MARS2 focuses on real-world and specialized scenarios to broaden the multimodal reasoning applications of MLLMs. Our organizing team released two tailored datasets Lens and AdsQA as test sets, which support general reasoning in 12 daily scenarios and domain-specific reasoning in advertisement videos, respectively. We evaluated 40+ baselines that include both generalist MLLMs and task-specific models, and opened up three competition tracks, i.e., Visual Grounding in Real-world Scenarios (VG-RS), Visual Question Answering with Spatial Awareness (VQA-SA), and Visual Reasoning in Creative Advertisement Videos (VR-Ads). Finally, 76 teams from the renowned academic and industrial institutions have registered and 40+ valid submissions (out of 1200+) have been included in our ranking lists. Our datasets, code sets (40+ baselines and 15+ participants' methods), and rankings are publicly available on the MARS2 workshop website and our GitHub organization page https://github.com/mars2workshop/, where our updates and announcements of upcoming events will be continuously provided.

Strawberry Robotic Operation Interface: An Open-Source Device for Collecting Dexterous Manipulation Data in Robotic Strawberry Farming

The strawberry farming is labor-intensive, particularly in tasks requiring dexterous manipulation such as picking occluded strawberries. To address this challenge, we present the Strawberry Robotic Operation Interface (SROI), an open-source device designed for collecting dexterous manipulation data in robotic strawberry farming. The SROI features a handheld unit with a modular end effector, a stereo robotic camera, enabling the easy collection of demonstration data in field environments. A data post-processing pipeline is introduced to extract spatial trajectories and gripper states from the collected data. Additionally, we release an open-source dataset of strawberry picking demonstrations to facilitate research in dexterous robotic manipulation. The SROI represents a step toward automating complex strawberry farming tasks, reducing reliance on manual labor.

Learn from Foundation Model: Fruit Detection Model without Manual Annotation

Recent breakthroughs in large foundation models have enabled the possibility of transferring knowledge pre-trained on vast datasets to domains with limited data availability. Agriculture is one of the domains that lacks sufficient data. This study proposes a framework to train effective, domain-specific, small models from foundation models without manual annotation. Our approach begins with SDM (Segmentation-Description-Matching), a stage that leverages two foundation models: SAM2 (Segment Anything in Images and Videos) for segmentation and OpenCLIP (Open Contrastive Language-Image Pretraining) for zero-shot open-vocabulary classification. In the second stage, a novel knowledge distillation mechanism is utilized to distill compact, edge-deployable models from SDM, enhancing both inference speed and perception accuracy. The complete method, termed SDM-D (Segmentation-Description-Matching-Distilling), demonstrates strong performance across various fruit detection tasks object detection, semantic segmentation, and instance segmentation) without manual annotation. It nearly matches the performance of models trained with abundant labels. Notably, SDM-D outperforms open-set detection methods such as Grounding SAM and YOLO-World on all tested fruit detection datasets. Additionally, we introduce MegaFruits, a comprehensive fruit segmentation dataset encompassing over 25,000 images, and all code and datasets are made publicly available at https://github.com/AgRoboticsResearch/SDM-D.git.

TTT4Rec: A Test-Time Training Approach for Rapid Adaption in Sequential Recommendation

Sequential recommendation tasks, which aim to predict the next item a user will interact with, typically rely on models trained solely on historical data. However, in real-world scenarios, user behavior can fluctuate in the long interaction sequences, and training data may be limited to model this dynamics. To address this, Test-Time Training (TTT) offers a novel approach by using self-supervised learning during inference to dynamically update model parameters. This allows the model to adapt to new user interactions in real-time, leading to more accurate recommendations. In this paper, we propose TTT4Rec, a sequential recommendation framework that integrates TTT to better capture dynamic user behavior. By continuously updating model parameters during inference, TTT4Rec is particularly effective in scenarios where user interaction sequences are long, training data is limited, or user behavior is highly variable. We evaluate TTT4Rec on three widely-used recommendation datasets, demonstrating that it achieves performance on par with or exceeding state-of-the-art models. The codes are available at https://github.com/ZhaoqiZachYang/TTT4Rec.

Top-down Activity Representation Learning for Video Question Answering

Capturing complex hierarchical human activities, from atomic actions (e.g., picking up one present, moving to the sofa, unwrapping the present) to contextual events (e.g., celebrating Christmas) is crucial for achieving high-performance video question answering (VideoQA). Recent works have expanded multimodal models (e.g., CLIP, LLaVA) to process continuous video sequences, enhancing the model's temporal reasoning capabilities. However, these approaches often fail to capture contextual events that can be decomposed into multiple atomic actions non-continuously distributed over relatively long-term sequences. In this paper, to leverage the spatial visual context representation capability of the CLIP model for obtaining non-continuous visual representations in terms of contextual events in videos, we convert long-term video sequences into a spatial image domain and finetune the multimodal model LLaVA for the VideoQA task. Our approach achieves competitive performance on the STAR task, in particular, with a 78.4% accuracy score, exceeding the current state-of-the-art score by 2.8 points on the NExTQA task.

Multi-object event graph representation learning for Video Question Answering

Video question answering (VideoQA) is a task to predict the correct answer to questions posed about a given video. The system must comprehend spatial and temporal relationships among objects extracted from videos to perform causal and temporal reasoning. While prior works have focused on modeling individual object movements using transformer-based methods, they falter when capturing complex scenarios involving multiple objects (e.g., "a boy is throwing a ball in a hoop"). We propose a contrastive language event graph representation learning method called CLanG to address this limitation. Aiming to capture event representations associated with multiple objects, our method employs a multi-layer GNN-cluster module for adversarial graph representation learning, enabling contrastive learning between the question text and its relevant multi-object event graph. Our method outperforms a strong baseline, achieving up to 2.2% higher accuracy on two challenging VideoQA datasets, NExT-QA and TGIF-QA-R. In particular, it is 2.8% better than baselines in handling causal and temporal questions, highlighting its strength in reasoning multiple object-based events.

Anchor-aware Deep Metric Learning for Audio-visual Retrieval

Metric learning minimizes the gap between similar (positive) pairs of data points and increases the separation of dissimilar (negative) pairs, aiming at capturing the underlying data structure and enhancing the performance of tasks like audio-visual cross-modal retrieval (AV-CMR). Recent works employ sampling methods to select impactful data points from the embedding space during training. However, the model training fails to fully explore the space due to the scarcity of training data points, resulting in an incomplete representation of the overall positive and negative distributions. In this paper, we propose an innovative Anchor-aware Deep Metric Learning (AADML) method to address this challenge by uncovering the underlying correlations among existing data points, which enhances the quality of the shared embedding space. Specifically, our method establishes a correlation graph-based manifold structure by considering the dependencies between each sample as the anchor and its semantically similar samples. Through dynamic weighting of the correlations within this underlying manifold structure using an attention-driven mechanism, Anchor Awareness (AA) scores are obtained for each anchor. These AA scores serve as data proxies to compute relative distances in metric learning approaches. Extensive experiments conducted on two audio-visual benchmark datasets demonstrate the effectiveness of our proposed AADML method, significantly surpassing state-of-the-art models. Furthermore, we investigate the integration of AA proxies with various metric learning methods, further highlighting the efficacy of our approach.

Amplitude-Phase Fusion for Enhanced Electrocardiogram Morphological Analysis

Considering the variability of amplitude and phase patterns in electrocardiogram (ECG) signals due to cardiac activity and individual differences, existing entropy-based studies have not fully utilized these two patterns and lack integration. To address this gap, this paper proposes a novel fusion entropy metric, morphological ECG entropy (MEE) for the first time, specifically designed for ECG morphology, to comprehensively describe the fusion of amplitude and phase patterns. MEE is computed based on beat-level samples, enabling detailed analysis of each cardiac cycle. Experimental results demonstrate that MEE achieves rapid, accurate, and label-free localization of abnormal ECG arrhythmia regions. Furthermore, MEE provides a method for assessing sample diversity, facilitating compression of imbalanced training sets (via representative sample selection), and outperforms random pruning. Additionally, MEE exhibits the ability to describe areas of poor quality. By discussing, it proves the robustness of MEE value calculation to noise interference and its low computational complexity. Finally, we integrate this method into a clinical interactive interface to provide a more convenient and intuitive user experience. These findings indicate that MEE serves as a valuable clinical descriptor for ECG characterization. The implementation code can be referenced at the following link: https://github.com/fdu-harry/ECG-MEE-metric.

TimeGraphs: Graph-based Temporal Reasoning

Many real-world systems exhibit temporal, dynamic behaviors, which are captured as time series of complex agent interactions. To perform temporal reasoning, current methods primarily encode temporal dynamics through simple sequence-based models. However, in general these models fail to efficiently capture the full spectrum of rich dynamics in the input, since the dynamics is not uniformly distributed. In particular, relevant information might be harder to extract and computing power is wasted for processing all individual timesteps, even if they contain no significant changes or no new information. Here we propose TimeGraphs, a novel approach that characterizes dynamic interactions as a hierarchical temporal graph, diverging from traditional sequential representations. Our approach models the interactions using a compact graph-based representation, enabling adaptive reasoning across diverse time scales. Adopting a self-supervised method, TimeGraphs constructs a multi-level event hierarchy from a temporal input, which is then used to efficiently reason about the unevenly distributed dynamics. This construction process is scalable and incremental to accommodate streaming data. We evaluate TimeGraphs on multiple datasets with complex, dynamic agent interactions, including a football simulator, the Resistance game, and the MOMA human activity dataset. The results demonstrate both robustness and efficiency of TimeGraphs on a range of temporal reasoning tasks. Our approach obtains state-of-the-art performance and leads to a performance increase of up to 12.2% on event prediction and recognition tasks over current approaches. Our experiments further demonstrate a wide array of capabilities including zero-shot generalization, robustness in case of data sparsity, and adaptability to streaming data flow.