Multimodal large language models (MLLMs) have rapidly advanced from perception tasks to complex multi-step reasoning, yet reinforcement learning with verifiable rewards (RLVR) often leads to spurious reasoning since only the final-answer correctness is rewarded. To address this limitation, we propose AutoRubric-R1V, a framework that integrates RLVR with process-level supervision through automatically collected rubric-based generative rewards. Our key innovation lies in a scalable self-aggregation method that distills consistent reasoning checkpoints from successful trajectories, enabling problem-specific rubric construction without human annotation or stronger teacher models. By jointly leveraging rubric-based and outcome rewards, AutoRubric-R1V achieves state-of-the-art performance on six multimodal reasoning benchmarks and substantially improves reasoning faithfulness in dedicated evaluations.

Artificial intelligence (AI) is rapidly transforming healthcare, enabling fast development of tools like stress monitors, wellness trackers, and mental health chatbots. However, rapid and low-barrier development can introduce risks of bias, privacy violations, and unequal access, especially when systems ignore real-world contexts and diverse user needs. Many recent methods use AI to detect risks automatically, but this can reduce human engagement in understanding how harms arise and who they affect. We present a human-centered framework that generates user stories and supports multi-agent discussions to help people think creatively about potential benefits and harms before deployment. In a user study, participants who read stories recognized a broader range of harms, distributing their responses more evenly across all 13 harm types. In contrast, those who did not read stories focused primarily on privacy and well-being (58.3%). Our findings show that storytelling helped participants speculate about a broader range of harms and benefits and think more creatively about AI's impact on users.

Large language models (LLMs) are increasingly demonstrating strong capabilities as autonomous agents, with function calling serving as a core mechanism for interaction with the environment. Meanwhile, inference scaling has become a cutting-edge technique to enhance LLM performance by allocating more computational resources during the inference process. However, current research on inference scaling primarily focuses on unstructured output generation tasks, leaving its application in structured outputs, like function calling, largely underexplored. To bridge this gap, we propose an inference scaling framework that combines fine-grained beam search with a process reward model, ToolPRM, which scores the internal steps of each single function call. To train ToolPRM, we construct the first fine-grained intra-call process supervision dataset, automatically annotated with function-masking techniques to provide step-level rewards for structured tool-use reasoning. Extensive experiments demonstrate that ToolPRM beats the coarse-grained and outcome reward models in terms of predictive accuracy, indicating its stronger capability in supervising the function calling inference process. Inference scaling technique equipped with ToolPRM also significantly improves the backbone model performance across various function calling tasks and benchmarks. More importantly, we reveal a key principle for applying inference scaling techniques to structured outputs: "explore more but retain less" due to the unrecoverability characteristics of structured function calling generation.

The next point-of-interest (POI) recommendation task aims to predict the users' immediate next destinations based on their preferences and historical check-ins, holding significant value in location-based services. Recently, large language models (LLMs) have shown great potential in recommender systems, which treat the next POI prediction in a generative manner. However, these LLMs, pretrained primarily on vast corpora of unstructured text, lack the native understanding of structured geographical entities and sequential mobility patterns required for next POI prediction tasks. Moreover, in industrial-scale POI prediction applications, incorporating world knowledge and alignment of human cognition, such as seasons, weather conditions, holidays, and users' profiles (such as habits, occupation, and preferences), can enhance the user experience while improving recommendation performance. To address these issues, we propose CoAST (Cognitive-Aligned Spatial-Temporal LLMs), a framework employing natural language as an interface, allowing for the incorporation of world knowledge, spatio-temporal trajectory patterns, profiles, and situational information. Specifically, CoAST mainly comprises of 2 stages: (1) Recommendation Knowledge Acquisition through continued pretraining on the enriched spatial-temporal trajectory data of the desensitized users; (2) Cognitive Alignment to align cognitive judgments with human preferences using enriched training data through Supervised Fine-Tuning (SFT) and a subsequent Reinforcement Learning (RL) phase. Extensive offline experiments on various real-world datasets and online experiments deployed in "Guess Where You Go" of AMAP App homepage demonstrate the effectiveness of CoAST.

Model merging aims to integrate task-specific abilities from individually fine-tuned models into a single model without extra training. In recent model merging methods, task vector has become a fundamental building block, as it can encapsulate the residual information from finetuning. However, the merged model often suffers from notable performance degradation due to the conflicts caused by task-irrelevant redundancy in task vectors. Existing efforts in overcoming redundancy by randomly dropping elements in the parameter space involves randomness and lacks knowledge awareness. To address these challenges, in this study, we propose Purifying TAsk Vectors (PAVE) in knowledge-aware subspace. Concretely, we sample some training examples from each task, and feed them into their corresponding fine-tuned models to acquire the covariance matrices before linear layers. We then perform a context-oriented singular value decomposition, which accentuates the weight components most relevant to the target knowledge. As a result, we can split fine-tuned model weights into task-relevant and redundant components in the knowledge-aware subspace, and purify the task vector by pruning the redundant components. To induce fair pruning efforts across models, we further introduce a spectral rank allocation strategy by optimizing a normalized activated pruning error. The task vector purification by our method as a plug-and-play scheme is applicable across various task vector-based merging methods to improve their performance. In experiments, we demonstrate the effectiveness of PAVE across a diverse set of merging methods, tasks, and model architectures.

We introduce xLLM, an intelligent and efficient Large Language Model (LLM) inference framework designed for high-performance, large-scale enterprise-grade serving, with deep optimizations for diverse AI accelerators. To address these challenges, xLLM builds a novel decoupled service-engine architecture. At the service layer, xLLM-Service features an intelligent scheduling module that efficiently processes multimodal requests and co-locates online and offline tasks through unified elastic scheduling to maximize cluster utilization. This module also relies on a workload-adaptive dynamic Prefill-Decode (PD) disaggregation policy and a novel Encode-Prefill-Decode (EPD) disaggregation policy designed for multimodal inputs. Furthermore, it incorporates a distributed architecture to provide global KV Cache management and robust fault-tolerant capabilities for high availability. At the engine layer, xLLM-Engine co-optimizes system and algorithm designs to fully saturate computing resources. This is achieved through comprehensive multi-layer execution pipeline optimizations, an adaptive graph mode and an xTensor memory management. xLLM-Engine also further integrates algorithmic enhancements such as optimized speculative decoding and dynamic EPLB, collectively serving to substantially boost throughput and inference efficiency. Extensive evaluations demonstrate that xLLM delivers significantly superior performance and resource efficiency. Under identical TPOT constraints, xLLM achieves throughput up to 1.7x that of MindIE and 2.2x that of vLLM-Ascend with Qwen-series models, while maintaining an average throughput of 1.7x that of MindIE with Deepseek-series models. xLLM framework is publicly available at https://github.com/jd-opensource/xllm and https://github.com/jd-opensource/xllm-service.

TITAN (Threat Intelligence Through Automated Navigation) is a framework that connects natural-language cyber-threat queries with executable reasoning over a structured knowledge graph. It integrates a path-planner model, which predicts logical relation chains from text, and a graph executor that traverses the TITAN Ontology to retrieve factual answers and supporting evidence. Unlike traditional retrieval systems, TITAN operates on a typed, bidirectional graph derived from MITRE ATT&CK, allowing reasoning to move clearly and reversibly between threats, behaviors, and defenses. To support training and evaluation, we introduce the TITAN Dataset, a corpus of 88,209 examples (Train: 74,258; Test: 13,951) pairing natural-language questions with executable reasoning paths and step-by-step Chain-of-Thought explanations. Empirical evaluations show that TITAN enables models to generate syntactically valid and semantically coherent reasoning paths that can be deterministically executed on the underlying graph.

Large language models (LLMs) are becoming deeply embedded in human communication and decision-making, yet they inherit the ambiguity, bias, and lack of direct access to truth inherent in language itself. While their outputs are fluent, emotionally resonant, and coherent, they are generated through statistical prediction rather than grounded reasoning. This creates the risk of hallucination, responses that sound convincing but lack factual validity. Building on Geoffrey Hinton's observation that AI mirrors human intuition rather than reasoning, this paper argues that LLMs operationalize System 1 cognition at scale: fast, associative, and persuasive, but without reflection or falsification. To address this, we introduce the Rose-Frame, a three-dimensional framework for diagnosing cognitive and epistemic drift in human-AI interaction. The three axes are: (i) Map vs. Territory, which distinguishes representations of reality (epistemology) from reality itself (ontology); (ii) Intuition vs. Reason, drawing on dual-process theory to separate fast, emotional judgments from slow, reflective thinking; and (iii) Conflict vs. Confirmation, which examines whether ideas are critically tested through disagreement or simply reinforced through mutual validation. Each dimension captures a distinct failure mode, and their combination amplifies misalignment. Rose-Frame does not attempt to fix LLMs with more data or rules. Instead, it offers a reflective tool that makes both the model's limitations and the user's assumptions visible, enabling more transparent and critically aware AI deployment. It reframes alignment as cognitive governance: intuition, whether human or artificial, must remain governed by human reason. Only by embedding reflective, falsifiable oversight can we align machine fluency with human understanding.

Despite the rapid progress of instruction-based image editing, its extension to video remains underexplored, primarily due to the prohibitive cost and complexity of constructing large-scale paired video editing datasets. To address this challenge, we introduce a low-cost pretraining strategy for instruction-based video editing that leverages in-context learning from unpaired video clips. We show that pretraining a foundation video generation model with this strategy endows it with general editing capabilities, such as adding, replacing, or deleting operations, according to input editing instructions. The pretrained model can then be efficiently refined with a small amount of high-quality paired editing data. Built upon HunyuanVideoT2V, our framework first pretrains on approximately 1M real video clips to learn basic editing concepts, and subsequently fine-tunes on fewer than 150k curated editing pairs to extend more editing tasks and improve the editing quality. Comparative experiments show that our method surpasses existing instruction-based video editing approaches in both instruction alignment and visual fidelity, achieving a 12\% improvement in editing instruction following and a 15\% improvement in editing quality.

ABSTRACT Text-To-Speech synthesis has achieved near-human quality in neutral speech, but emotional expressiveness remains a challenge. Existing methods often rely on costly emotion annotations or optimize indirect objectives that fail to capture the emotional expressiveness and perceptual naturalness of speech, leading to generated speech that is accurate but emotionally flat. To address these challenges, we propose the RLAIF-SPA framework, incorporating a Reinforcement Learning from AI Feedback (RLAIF) mechanism to employ Automatic Speech Recognition (ASR) and Large Language Model (LLM) techniques to respectively judge semantic accuracy and prosodic-emotional label alignment as a direct reward for emotional expressiveness and intelligibility optimization. Specifically, it leverages Prosodic Label Alignment to enhance expressive quality by jointly considering semantic accuracy and prosodic-emotional alignment along four fine-grained dimensions: Structure, Emotion, Speed, and T one. In addition, it incorporates Semantic Accuracy Feedback to ensure the generation of clear and accurate speech. Experiments on the LibriSpeech dataset show that RLAIF-SP A outperforms Chat-TTS, with a 26.1% reduction in WER, a 9.1% increase in SIM-O, and over 10% improvement in human evaluation.