From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation

Accurate process supervision remains a critical challenge for long-horizon robotic manipulation. A primary bottleneck is that current video MLLMs, trained primarily under a Supervised Fine-Tuning (SFT) paradigm, function as passive "Observers" that recognize ongoing events rather than evaluating the current state relative to the final task goal. In this paper, we introduce PRIMO R1 (Process Reasoning Induced Monitoring), a 7B framework that transforms video MLLMs into active "Critics". We leverage outcome-based Reinforcement Learning to incentivize explicit Chain-of-Thought generation for progress estimation. Furthermore, our architecture constructs a structured temporal input by explicitly anchoring the video sequence between initial and current state images. Supported by the proposed PRIMO Dataset and Benchmark, extensive experiments across diverse in-domain environments and out-of-domain real-world humanoid scenarios demonstrate that PRIMO R1 achieves state-of-the-art performance. Quantitatively, our 7B model achieves a 50% reduction in the mean absolute error of specialized reasoning baselines, demonstrating significant relative accuracy improvements over 72B-scale general MLLMs. Furthermore, PRIMO R1 exhibits strong zero-shot generalization on difficult failure detection tasks. We establish state-of-the-art performance on RoboFail benchmark with 67.0% accuracy, surpassing closed-source models like OpenAI o1 by 6.0%.

Load-Aware Locomotion Control for Humanoid Robots in Industrial Transportation Tasks

Humanoid robots deployed in industrial environments are required to perform load-carrying transportation tasks that tightly couple locomotion and manipulation. However, achieving stable and robust locomotion under varying payloads and upper-body motions is challenging due to dynamic coupling and partial observability. This paper presents a load-aware locomotion framework for industrial humanoids based on a decoupled yet coordinated loco-manipulation architecture. Lower-body locomotion is controlled via a reinforcement learning policy producing residual joint actions on kinematically derived nominal configurations. A kinematics-based locomotion reference with a height-conditioned joint-space offset guides learning, while a history-based state estimator infers base linear velocity and height and encodes residual load- and manipulation-induced disturbances in a compact latent representation. The framework is trained entirely in simulation and deployed on a full-size humanoid robot without fine-tuning. Simulation and real-world experiments demonstrate faster training, accurate height tracking, and stable loco-manipulation. Project page: https://lequn-f.github.io/LALO/

R3DP: Real-Time 3D-Aware Policy for Embodied Manipulation

Embodied manipulation requires accurate 3D understanding of objects and their spatial relations to plan and execute contact-rich actions. While large-scale 3D vision models provide strong priors, their computational cost incurs prohibitive latency for real-time control. We propose Real-time 3D-aware Policy (R3DP), which integrates powerful 3D priors into manipulation policies without sacrificing real-time performance. A core innovation of R3DP is the asynchronous fast-slow collaboration module, which seamlessly integrates large-scale 3D priors into the policy without compromising real-time performance. The system maintains real-time efficiency by querying the pre-trained slow system (VGGT) only on sparse key frames, while simultaneously employing a lightweight Temporal Feature Prediction Network (TFPNet) to predict features for all intermediate frames. By leveraging historical data to exploit temporal correlations, TFPNet explicitly improves task success rates through consistent feature estimation. Additionally, to enable more effective multi-view fusion, we introduce a Multi-View Feature Fuser (MVFF) that aggregates features across views by explicitly incorporating camera intrinsics and extrinsics. R3DP offers a plug-and-play solution for integrating large models into real-time inference systems. We evaluate R3DP against multiple baselines across different visual configurations. R3DP effectively harnesses large-scale 3D priors to achieve superior results, outperforming single-view and multi-view DP by 32.9% and 51.4% in average success rate, respectively. Furthermore, by decoupling heavy 3D reasoning from policy execution, R3DP achieves a 44.8% reduction in inference time compared to a naive DP+VGGT integration.

Hierarchical Interaction Summarization and Contrastive Prompting for Explainable Recommendations

Explainable recommendations, which use the information of user and item with interaction to generate a explanation for why the user would interact with the item, are crucial for improving user trust and decision transparency to the recommender system. Existing methods primarily rely on encoding features of users and items to embeddings, which often leads to information loss due to dimensionality reduction, sparse interactions, and so on. With the advancements of large language models (LLMs) in language comprehension, some methods use embeddings as LLM inputs for explanation generation. However, since embeddings lack inherent semantics, LLMs must adjust or extend their parameters to interpret them, a process that inevitably incurs information loss. To address this issue, we propose a novel approach combining profile generation via hierarchical interaction summarization (PGHIS), which leverages a pretrained LLM to hierarchically summarize user-item interactions, generating structured textual profiles as explicit representations of user and item characteristics. Additionally, we propose contrastive prompting for explanation generation (CPEG) which employs contrastive learning to guide another reasoning language models in producing high-quality ground truth recommendation explanations. Finally, we use the textual profiles of user and item as input and high-quality explanation as output to fine-tune a LLM for generating explanations. Experimental results on multiple datasets demonstrate that our approach outperforms existing state-of-the-art methods, achieving a great improvement on metrics about explainability (e.g., 5% on GPTScore) and text quality. Furthermore, our generated ground truth explanations achieve a significantly higher win rate compared to user-written reviews and those produced by other methods, demonstrating the effectiveness of CPEG in generating high-quality ground truths.

A Framework For Image Synthesis Using Supervised Contrastive Learning

Text-to-image (T2I) generation aims at producing realistic images corresponding to text descriptions. Generative Adversarial Network (GAN) has proven to be successful in this task. Typical T2I GANs are 2 phase methods that first pretrain an inter-modal representation from aligned image-text pairs and then use GAN to train image generator on that basis. However, such representation ignores the inner-modal semantic correspondence, e.g. the images with same label. The semantic label in priory describes the inherent distribution pattern with underlying cross-image relationships, which is supplement to the text description for understanding the full characteristics of image. In this paper, we propose a framework leveraging both inter- and inner-modal correspondence by label guided supervised contrastive learning. We extend the T2I GANs to two parameter-sharing contrast branches in both pretraining and generation phases. This integration effectively clusters the semantically similar image-text pair representations, thereby fostering the generation of higher-quality images. We demonstrate our framework on four novel T2I GANs by both single-object dataset CUB and multi-object dataset COCO, achieving significant improvements in the Inception Score (IS) and Frechet Inception Distance (FID) metrics of imagegeneration evaluation. Notably, on more complex multi-object COCO, our framework improves FID by 30.1%, 27.3%, 16.2% and 17.1% for AttnGAN, DM-GAN, SSA-GAN and GALIP, respectively. We also validate our superiority by comparing with other label guided T2I GANs. The results affirm the effectiveness and competitiveness of our approach in advancing the state-of-the-art GAN for T2I generation

ActiveRAG: Revealing the Treasures of Knowledge via Active Learning

Retrieval Augmented Generation (RAG) has introduced a new paradigm for Large Language Models (LLMs), aiding in the resolution of knowledge-intensive tasks. However, current RAG models position LLMs as passive knowledge receptors, thereby restricting their capacity for learning and comprehending external knowledge. In this paper, we present ActiveRAG, an innovative RAG framework that shifts from passive knowledge acquisition to an active learning mechanism. This approach utilizes the Knowledge Construction mechanism to develop a deeper understanding of external knowledge by associating it with previously acquired or memorized knowledge. Subsequently, it designs the Cognitive Nexus mechanism to incorporate the outcomes from both chains of thought and knowledge construction, thereby calibrating the intrinsic cognition of LLMs. Our experimental results demonstrate that ActiveRAG surpasses previous RAG models, achieving a 5% improvement on question-answering datasets. All data and codes are available at https://github.com/OpenMatch/ActiveRAG.

Weaver: Foundation Models for Creative Writing

This work introduces Weaver, our first family of large language models (LLMs) dedicated to content creation. Weaver is pre-trained on a carefully selected corpus that focuses on improving the writing capabilities of large language models. We then fine-tune Weaver for creative and professional writing purposes and align it to the preference of professional writers using a suit of novel methods for instruction data synthesis and LLM alignment, making it able to produce more human-like texts and follow more diverse instructions for content creation. The Weaver family consists of models of Weaver Mini (1.8B), Weaver Base (6B), Weaver Pro (14B), and Weaver Ultra (34B) sizes, suitable for different applications and can be dynamically dispatched by a routing agent according to query complexity to balance response quality and computation cost. Evaluation on a carefully curated benchmark for assessing the writing capabilities of LLMs shows Weaver models of all sizes outperform generalist LLMs several times larger than them. Notably, our most-capable Weaver Ultra model surpasses GPT-4, a state-of-the-art generalist LLM, on various writing scenarios, demonstrating the advantage of training specialized LLMs for writing purposes. Moreover, Weaver natively supports retrieval-augmented generation (RAG) and function calling (tool usage). We present various use cases of these abilities for improving AI-assisted writing systems, including integration of external knowledge bases, tools, or APIs, and providing personalized writing assistance. Furthermore, we discuss and summarize a guideline and best practices for pre-training and fine-tuning domain-specific LLMs.

Connecting Software Metrics across Versions to Predict Defects

Accurate software defect prediction could help software practitioners allocate test resources to defect-prone modules effectively and efficiently. In the last decades, much effort has been devoted to build accurate defect prediction models, including developing quality defect predictors and modeling techniques. However, current widely used defect predictors such as code metrics and process metrics could not well describe how software modules change over the project evolution, which we believe is important for defect prediction. In order to deal with this problem, in this paper, we propose to use the Historical Version Sequence of Metrics (HVSM) in continuous software versions as defect predictors. Furthermore, we leverage Recurrent Neural Network (RNN), a popular modeling technique, to take HVSM as the input to build software prediction models. The experimental results show that, in most cases, the proposed HVSM-based RNN model has a significantly better effort-aware ranking effectiveness than the commonly used baseline models.