Then, we perform sequential reasoning over the graph, iteratively traversing its nodes to answer a given question or draw a new inference.

Modelling of human preferences is an important step in modern post-training pipelines for AI alignment. One popular approach of building such models of human preference is assuming that human preference rankings assume a Plackett-Luce (Plackett, 1975; Luce et al., 1959) distribution. In this monograph, I draw a somewhat remarkable connection of the popular statistical model for estimating lifetimes, the Cox Proportional Hazard model (Cox, 1972) to the Plackett-Luce model and then consequently to algorithms such as Direct Preference Optimization, a popular algorithm for aligning modern Artifical Intelligence (Ouyang et al., 2022). To the best of my knowledge, at the time of writing the connection between the Proportional Hazards model and the Plackett-Luce is relatively little known, and the subsequent connections to the AI alignment algorithms such as'Direct Preference Optimization ' (Rafailov et al., 2023) are not well appreciated. I believe that explcitly stating this connection will help the AI research community build on existing research in semi-parametric statistics to build better models of human preference.

Embodied AI (EAI) agents continuously interact with the physical world, generating vast, heterogeneous multimodal data streams that traditional management systems are ill-equipped to handle. In this survey, we first systematically evaluate five storage architectures (Graph Databases, Multi-Model Databases, Data Lakes, Vector Databases, and Time-Series Databases), focusing on their suitability for addressing EAI's core requirements, including physical grounding, low-latency access, and dynamic scalability. We then analyze five retrieval paradigms (Fusion Strategy-Based Retrieval, Representation Alignment-Based Retrieval, Graph-Structure-Based Retrieval, Generation Model-Based Retrieval, and Efficient Retrieval-Based Optimization), revealing a fundamental tension between achieving long-term semantic coherence and maintaining real-time responsiveness. Based on this comprehensive analysis, we identify key bottlenecks, spanning from the foundational Physical Grounding Gap to systemic challenges in cross-modal integration, dynamic adaptation, and open-world generalization. Finally, we outline a forward-looking research agenda encompassing physics-aware data models, adaptive storage-retrieval co-optimization, and standardized benchmarking, to guide future research toward principled data management solutions for EAI. Our survey is based on a comprehensive review of more than 180 related studies, providing a rigorous roadmap for designing the robust, high-performance data management frameworks essential for the next generation of autonomous embodied systems.

Vision-language models (VLMs) have emerged as powerful tools for enabling automated traffic analysis; however, current approaches often demand substantial computational resources and struggle with fine-grained spatio-temporal understanding. This paper introduces STER-VLM, a computationally efficient framework that enhances VLM performance through (1) caption decomposition to tackle spatial and temporal information separately, (2) temporal frame selection with best-view filtering for sufficient temporal information, and (3) reference-driven understanding for capturing fine-grained motion and dynamic context and (4) curated visual/textual prompt techniques. Experimental results on the WTS \cite{kong2024wts} and BDD \cite{BDD} datasets demonstrate substantial gains in semantic richness and traffic scene interpretation. Our framework is validated through a decent test score of 55.655 in the AI City Challenge 2025 Track 2, showing its effectiveness in advancing resource-efficient and accurate traffic analysis for real-world applications.

We present Datarus-R1-14B, a 14 B-parameter open-weights language model fine-tuned from Qwen 2.5-14B-Instruct to act as a virtual data analyst and graduate-level problem solver. Datarus is trained not on isolated question-answer pairs but on full analytical trajectories including reasoning steps, code execution, error traces, self-corrections, and final conclusions, all captured in a ReAct-style notebook format spanning finance, medicine, numerical analysis, and other quantitative domains. Our training pipeline combines (i) a trajectory-centric synthetic data generator that yielded 144 000 tagged notebook episodes, (ii) a dual-reward framework blending a lightweight tag-based structural signal with a Hierarchical Reward Model (HRM) that scores both single-step soundness and end-to-end coherence, and (iii) a memory-optimized implementation of Group Relative Policy Optimization (GRPO) featuring KV-cache reuse, sequential generation, and reference-model sharding. A cosine curriculum smoothly shifts emphasis from structural fidelity to semantic depth, reducing the format collapse and verbosity that often plague RL-aligned LLMs. A central design choice in Datarus is it dual reasoning interface. In agentic mode the model produces ReAct-tagged steps that invoke Python tools to execute real code; in reflection mode it outputs compact Chain-of-Thought (CoT) traces delimited by and tags. On demanding postgraduate-level problems, Datarus exhibits an "AHA-moment" pattern: it sketches hypotheses, revises them once or twice, and converges avoiding the circular, token-inflating loops common to contemporary systems. Across standard public benchmarks Datarus surpasses similar size models and even reaches the level of larger reasoning models such as QwQ-32B achieving up to 30% higher accuracy on AIME 2024/2025 and LiveCodeBench while emitting 18-49% fewer tokens per solution.

In large language model-based agents, memory serves as a critical capability for achieving personalization by storing and utilizing users' information. Although some previous studies have adopted memory to implement user personalization, they typically focus on preference alignment and simple question-answering. However, in the real world, complex tasks often require multi-hop reasoning on a large amount of user information, which poses significant challenges for current memory approaches. To address this limitation, we propose the multi-hop personalized reasoning task to explore how different memory mechanisms perform in multi-hop reasoning over personalized information. We explicitly define this task and construct a dataset along with a unified evaluation framework. Then, we implement various explicit and implicit memory methods and conduct comprehensive experiments. We evaluate their performance on this task from multiple perspectives and analyze their strengths and weaknesses. Besides, we explore hybrid approaches that combine both paradigms and propose the HybridMem method to address their limitations. We demonstrate the effectiveness of our proposed model through extensive experiments. To benefit the research community, we release this project at https://github.com/nuster1128/MPR.

The spreading of AI-generated images (AIGI), driven by advances in generative AI, poses a significant threat to information security and public trust. Existing AIGI detectors, while effective against images in clean laboratory settings, fail to generalize to in-the-wild scenarios. These real-world images are noisy, varying from ``obviously fake" images to realistic ones derived from multiple generative models and further edited for quality control. We address in-the-wild AIGI detection in this paper. We introduce Mirage, a challenging benchmark designed to emulate the complexity of in-the-wild AIGI. Mirage is constructed from two sources: (1) a large corpus of Internet-sourced AIGI verified by human experts, and (2) a synthesized dataset created through the collaboration between multiple expert generators, closely simulating the realistic AIGI in the wild. Building on this benchmark, we propose Mirage-R1, a vision-language model with heuristic-to-analytic reasoning, a reflective reasoning mechanism for AIGI detection. Mirage-R1 is trained in two stages: a supervised-fine-tuning cold start, followed by a reinforcement learning stage. By further adopting an inference-time adaptive thinking strategy, Mirage-R1 is able to provide either a quick judgment or a more robust and accurate conclusion, effectively balancing inference speed and performance. Extensive experiments show that our model leads state-of-the-art detectors by 5% and 10% on Mirage and the public benchmark, respectively. The benchmark and code will be made publicly available.

Large Language Models (LLMs) have demonstrated great potential in automating the generation of Verilog hardware description language code for hardware design. This automation is critical to reducing human effort in the complex and error-prone process of hardware design. However, existing approaches predominantly rely on human intervention and fine-tuning using curated datasets, limiting their scalability in automated design workflows. Although recent iterative search techniques have emerged, they often fail to explore diverse design solutions and may underperform simpler approaches such as repeated prompting. To address these limitations, we introduce EvoVerilog, a novel framework that combines the reasoning capabilities of LLMs with evolutionary algorithms to automatically generate and refine Verilog code. EvoVerilog utilizes a multiobjective, population-based search strategy to explore a wide range of design possibilities without requiring human intervention. Extensive experiments demonstrate that EvoVerilog achieves state-of-the-art performance, with pass@10 scores of 89.1 and 80.2 on the VerilogEval-Machine and VerilogEval-Human benchmarks, respectively. Furthermore, the framework showcases its ability to explore diverse designs by simultaneously generating a variety of functional Verilog code while optimizing resource utilization.

Legal Artificial Intelligence (LegalAI) has achieved notable advances in automating judicial decision-making with the support of Large Language Models (LLMs). However, existing legal LLMs still struggle to generate reliable and interpretable reasoning processes. They often default to fast-thinking behavior by producing direct answers without explicit multi-step reasoning, limiting their effectiveness in complex legal scenarios that demand rigorous justification. To address this challenge, we propose Legal$Δ$, a reinforcement learning framework designed to enhance legal reasoning through chain-of-thought guided information gain. During training, Legal$Δ$ employs a dual-mode input setup-comprising direct answer and reasoning-augmented modes-and maximizes the information gain between them. This encourages the model to acquire meaningful reasoning patterns rather than generating superficial or redundant explanations. Legal$Δ$ follows a two-stage approach: (1) distilling latent reasoning capabilities from a powerful Large Reasoning Model (LRM), DeepSeek-R1, and (2) refining reasoning quality via differential comparisons, combined with a multidimensional reward mechanism that assesses both structural coherence and legal-domain specificity. Experimental results on multiple legal reasoning tasks demonstrate that Legal$Δ$ outperforms strong baselines in both accuracy and interpretability. It consistently produces more robust and trustworthy legal judgments without relying on labeled preference data. All code and data will be released at https://github.com/NEUIR/LegalDelta.

Gaussian Splatting has rapidly emerged as a transformative technique for real-time 3D scene representation, offering a highly efficient and expressive alternative to Neural Radiance Fields (NeRF). Its ability to render complex scenes with high fidelity has enabled progress across domains such as scene reconstruction, robotics, and interactive content creation. More recently, the integration of Large Language Models (LLMs) and language embeddings into Gaussian Splatting pipelines has opened new possibilities for text-conditioned generation, editing, and semantic scene understanding. Despite these advances, a comprehensive overview of this emerging intersection has been lacking. This survey presents a structured review of current research efforts that combine language guidance with 3D Gaussian Splatting, detailing theoretical foundations, integration strategies, and real-world use cases. We highlight key limitations such as computational bottlenecks, generalizability, and the scarcity of semantically annotated 3D Gaussian data and outline open challenges and future directions for advancing language-guided 3D scene understanding using Gaussian Splatting.