Prefix Probing: Lightweight Harmful Content Detection for Large Language Models

Large language models often face a three-way trade-off among detection accuracy, inference latency, and deployment cost when used in real-world safety-sensitive applications. This paper introduces Prefix Probing, a black-box harmful content detection method that compares the conditional log-probabilities of "agreement/execution" versus "refusal/safety" opening prefixes and leverages prefix caching to reduce detection overhead to near first-token latency. During inference, the method requires only a single log-probability computation over the probe prefixes to produce a harmfulness score and apply a threshold, without invoking any additional models or multi-stage inference. To further enhance the discriminative power of the prefixes, we design an efficient prefix construction algorithm that automatically discovers highly informative prefixes, substantially improving detection performance. Extensive experiments demonstrate that Prefix Probing achieves detection effectiveness comparable to mainstream external safety models while incurring only minimal computational cost and requiring no extra model deployment, highlighting its strong practicality and efficiency.

Design, Results and Industry Implications of the World's First Insurance Large Language Model Evaluation Benchmark

This paper comprehensively elaborates on the construction methodology, multi-dimensional evaluation system, and underlying design philosophy of CUFEInse v1.0. Adhering to the principles of "quantitative-oriented, expert-driven, and multi-validation," the benchmark establishes an evaluation framework covering 5 core dimensions, 54 sub-indicators, and 14,430 high-quality questions, encompassing insurance theoretical knowledge, industry understanding, safety and compliance, intelligent agent application, and logical rigor. Based on this benchmark, a comprehensive evaluation was conducted on 11 mainstream large language models. The evaluation results reveal that general-purpose models suffer from common bottlenecks such as weak actuarial capabilities and inadequate compliance adaptation. High-quality domain-specific training demonstrates significant advantages in insurance vertical scenarios but exhibits shortcomings in business adaptation and compliance. The evaluation also accurately identifies the common bottlenecks of current large models in professional scenarios such as insurance actuarial, underwriting and claim settlement reasoning, and compliant marketing copywriting. The establishment of CUFEInse not only fills the gap in professional evaluation benchmarks for the insurance field, providing academia and industry with a professional, systematic, and authoritative evaluation tool, but also its construction concept and methodology offer important references for the evaluation paradigm of large models in vertical fields, serving as an authoritative reference for academic model optimization and industrial model selection. Finally, the paper looks forward to the future iteration direction of the evaluation benchmark and the core development direction of "domain adaptation + reasoning enhancement" for insurance large models.

Generative World Modelling for Humanoids: 1X World Model Challenge Technical Report

World models are a powerful paradigm in AI and robotics, enabling agents to reason about the future by predicting visual observations or compact latent states. The 1X World Model Challenge introduces an open-source benchmark of real-world humanoid interaction, with two complementary tracks: sampling, focused on forecasting future image frames, and compression, focused on predicting future discrete latent codes. For the sampling track, we adapt the video generation foundation model Wan-2.2 TI2V-5B to video-state-conditioned future frame prediction. We condition the video generation on robot states using AdaLN-Zero, and further post-train the model using LoRA. For the compression track, we train a Spatio-Temporal Transformer model from scratch. Our models achieve 23.0 dB PSNR in the sampling task and a Top-500 CE of 6.6386 in the compression task, securing 1st place in both challenges.

EasySize: Elastic Analog Circuit Sizing via LLM-Guided Heuristic Search

Analog circuit design is a time-consuming, experience-driven task in chip development. Despite advances in AI, developing universal, fast, and stable gate sizing methods for analog circuits remains a significant challenge. Recent approaches combine Large Language Models (LLMs) with heuristic search techniques to enhance generalizability, but they often depend on large model sizes and lack portability across different technology nodes. To overcome these limitations, we propose EasySize, the first lightweight gate sizing framework based on a finetuned Qwen3-8B model, designed for universal applicability across process nodes, design specifications, and circuit topologies. EasySize exploits the varying Ease of Attainability (EOA) of performance metrics to dynamically construct task-specific loss functions, enabling efficient heuristic search through global Differential Evolution (DE) and local Particle Swarm Optimization (PSO) within a feedback-enhanced flow. Although finetuned solely on 350nm node data, EasySize achieves strong performance on 5 operational amplifier (Op-Amp) netlists across 180nm, 45nm, and 22nm technology nodes without additional targeted training, and outperforms AutoCkt, a widely-used Reinforcement Learning based sizing framework, on 86.67\% of tasks with more than 96.67\% of simulation resources reduction. We argue that EasySize can significantly reduce the reliance on human expertise and computational resources in gate sizing, thereby accelerating and simplifying the analog circuit design process. EasySize will be open-sourced at a later date.

Slot Attention with Re-Initialization and Self-Distillation

Unlike popular solutions based on dense feature maps, Object-Centric Learning (OCL) represents visual scenes as sub-symbolic object-level feature vectors, termed slots, which are highly versatile for tasks involving visual modalities. OCL typically aggregates object superpixels into slots by iteratively applying competitive cross attention, known as Slot Attention, with the slots as the query. However, once initialized, these slots are reused naively, causing redundant slots to compete with informative ones for representing objects. This often results in objects being erroneously segmented into parts. Additionally, mainstream methods derive supervision signals solely from decoding slots into the input's reconstruction, overlooking potential supervision based on internal information. To address these issues, we propose Slot Attention with re-Initialization and self-Distillation (DIAS): $\emph{i)}$ We reduce redundancy in the aggregated slots and re-initialize extra aggregation to update the remaining slots; $\emph{ii)}$ We drive the bad attention map at the first aggregation iteration to approximate the good at the last iteration to enable self-distillation. Experiments demonstrate that DIAS achieves state-of-the-art on OCL tasks like object discovery and recognition, while also improving advanced visual prediction and reasoning. Our code is available on https://github.com/Genera1Z/DIAS.

IAM: Efficient Inference through Attention Mapping between Different-scale LLMs

LLMs encounter significant challenges in resource consumption nowadays, especially with long contexts. Despite extensive efforts dedicate to enhancing inference efficiency, these methods primarily exploit internal sparsity within the models, without leveraging external information for optimization. We identify the high similarity of attention matrices across different-scale LLMs, which offers a novel perspective for optimization. We first conduct a comprehensive analysis of how to measure similarity, how to select mapping Layers and whether mapping is consistency. Based on these insights, we introduce the IAM framework, which achieves dual benefits of accelerated attention computation and reduced KV cache usage by performing attention mapping between small and large LLMs. Our experimental results demonstrate that IAM can accelerate prefill by 15% and reduce KV cache usage by 22.1% without appreciably sacrificing performance. Experiments on different series of models show the generalizability of IAM. Importantly, it is also orthogonal to many existing KV cache optimization methods, making it a versatile addition to the current toolkit for enhancing LLM efficiency.

DAC: A Dynamic Attention-aware Approach for Task-Agnostic Prompt Compression

Task-agnostic prompt compression leverages the redundancy in natural language to reduce computational overhead and enhance information density within prompts, especially in long-context scenarios. Existing methods predominantly rely on information entropy as the metric to compress lexical units, aiming to achieve minimal information loss. However, these approaches overlook two critical aspects: (i) the importance of attention-critical tokens at the algorithmic level, and (ii) shifts in information entropy during the compression process. Motivated by these challenges, we propose a dynamic attention-aware approach for task-agnostic prompt compression (DAC). This approach effectively integrates entropy and attention information, dynamically sensing entropy shifts during compression to achieve fine-grained prompt compression. Extensive experiments across various domains, including LongBench, GSM8K, and BBH, show that DAC consistently yields robust and substantial improvements across a diverse range of tasks and LLMs, offering compelling evidence of its efficacy.

Pegasus: A Universal Framework for Scalable Deep Learning Inference on the Dataplane

The paradigm of Intelligent DataPlane (IDP) embeds deep learning (DL) models on the network dataplane to enable intelligent traffic analysis at line-speed. However, the current use of the match-action table (MAT) abstraction on the dataplane is misaligned with DL inference, leading to several key limitations, including accuracy degradation, limited scale, and lack of generality. This paper proposes Pegasus to address these limitations. Pegasus translates DL operations into three dataplane-oriented primitives to achieve generality: Partition, Map, and SumReduce. Specifically, Partition "divides" high-dimensional features into multiple low-dimensional vectors, making them more suitable for the dataplane; Map "conquers" computations on the low-dimensional vectors in parallel with the technique of fuzzy matching, while SumReduce "combines" the computation results. Additionally, Pegasus employs Primitive Fusion to merge computations, improving scalability. Finally, Pegasus adopts full precision weights with fixed-point activations to improve accuracy. Our implementation on a P4 switch demonstrates that Pegasus can effectively support various types of DL models, including Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), and AutoEncoder models on the dataplane. Meanwhile, Pegasus outperforms state-of-the-art approaches with an average accuracy improvement of up to 22.8%, along with up to 248x larger model size and 212x larger input scale.

LaF-GRPO: In-Situ Navigation Instruction Generation for the Visually Impaired via GRPO with LLM-as-Follower Reward

Navigation instruction generation for visually impaired (VI) individuals (NIG-VI) is critical yet relatively underexplored. This study, hence, focuses on producing precise, in-situ, step-by-step navigation instructions that are practically usable by VI users. Concretely, we propose LaF-GRPO (LLM-as-Follower GRPO), where an LLM simulates VI user responses to generate rewards guiding the Vision-Language Model (VLM) post-training. This enhances instruction usability while reducing costly real-world data needs. To facilitate training and testing, we introduce NIG4VI, a 27k-sample open-sourced benchmark. It provides diverse navigation scenarios with accurate spatial coordinates, supporting detailed, open-ended in-situ instruction generation. Experiments on NIG4VI show the effectiveness of LaF-GRPO by quantitative metrics (e.g., Zero-(LaF-GRPO) boosts BLEU +14\%; SFT+(LaF-GRPO) METEOR 0.542 vs. GPT-4o's 0.323) and yields more intuitive, safer instructions. Code and benchmark are available at \href{https://github.com/YiyiyiZhao/NIG4VI}{https://github.com/YiyiyiZhao/NIG4VI}.

SC4ANM: Identifying Optimal Section Combinations for Automated Novelty Prediction in Academic Papers

Novelty is a core component of academic papers, and there are multiple perspectives on the assessment of novelty. Existing methods often focus on word or entity combinations, which provide limited insights. The content related to a paper's novelty is typically distributed across different core sections, e.g., Introduction, Methodology and Results. Therefore, exploring the optimal combination of sections for evaluating the novelty of a paper is important for advancing automated novelty assessment. In this paper, we utilize different combinations of sections from academic papers as inputs to drive language models to predict novelty scores. We then analyze the results to determine the optimal section combinations for novelty score prediction. We first employ natural language processing techniques to identify the sectional structure of academic papers, categorizing them into introduction, methods, results, and discussion (IMRaD). Subsequently, we used different combinations of these sections (e.g., introduction and methods) as inputs for pretrained language models (PLMs) and large language models (LLMs), employing novelty scores provided by human expert reviewers as ground truth labels to obtain prediction results. The results indicate that using introduction, results and discussion is most appropriate for assessing the novelty of a paper, while the use of the entire text does not yield significant results. Furthermore, based on the results of the PLMs and LLMs, the introduction and results appear to be the most important section for the task of novelty score prediction. The code and dataset for this paper can be accessed at https://github.com/njust-winchy/SC4ANM.