Read As Human: Compressing Context via Parallelizable Close Reading and Skimming

Large Language Models (LLMs) demonstrate exceptional capability across diverse tasks. However, their deployment in long-context scenarios is hindered by two challenges: computational inefficiency and redundant information. We propose RAM (Read As HuMan), a context compression framework that adopts an adaptive hybrid reading strategy, to address these challenges. Inspired by human reading behavior (i.e., close reading important content while skimming less relevant content), RAM partitions the context into segments and encodes them with the input query in parallel. High-relevance segments are fully retained (close reading), while low-relevance ones are query-guided compressed into compact summary vectors (skimming). Both explicit textual segments and implicit summary vectors are concatenated and fed into decoder to achieve both superior performance and natural language format interpretability. To refine the decision boundary between close reading and skimming, we further introduce a contrastive learning objective based on positive and negative query-segment pairs. Experiments demonstrate that RAM outperforms existing baselines on multiple question answering and summarization benchmarks across two backbones, while delivering up to a 12x end-to-end speedup on long inputs (average length 16K; maximum length 32K).

COMI: Coarse-to-fine Context Compression via Marginal Information Gain

Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse tasks. However, their deployment in long context scenarios remains hindered by computational inefficiency and information redundancy. Context compression methods address these challenges by significantly reducing input length and eliminating redundancy. We propose COMI, a coarse-to-fine adaptive context compression framework that jointly optimizes for semantic relevance and diversity under high compression rates. We introduce Marginal Information Gain (MIG), a metric defined as the relevance of a unit to the input query minus its semantic redundancy with other units, guiding the compression process to prioritize information that is both relevant and low redundant. The framework operates in two stages: (1) Coarse-Grained Group Reallocation, where the context is partitioned into groups and dynamically assigned compression rates based on inter-group MIG, ensuring compression budgets align with information value distribution; and (2) Fine-Grained Token Merging, where tokens within each group are fused via an intra-group MIG-based weighting mechanism, thereby preserving key semantics while avoiding the accumulation of redundancy. Extensive experiments across question-answering (e.g., NaturalQuestions, 2WikiMQA, HotpotQA and NarrativeQA), summarization (e.g., MultiNews) with various backbones (e.g., LLaMA-2-7B, Qwen2-7B) show that COMI outperforms existing baselines by a large margin, e.g., approximately 25-point Exact Match (EM) improvement under 32x compression constraint with Qwen2-7B on NaturalQuestions.

MALLOC: Benchmarking the Memory-aware Long Sequence Compression for Large Sequential Recommendation

The scaling law, which indicates that model performance improves with increasing dataset and model capacity, has fueled a growing trend in expanding recommendation models in both industry and academia. However, the advent of large-scale recommenders also brings significantly higher computational costs, particularly under the long-sequence dependencies inherent in the user intent of recommendation systems. Current approaches often rely on pre-storing the intermediate states of the past behavior for each user, thereby reducing the quadratic re-computation cost for the following requests. Despite their effectiveness, these methods often treat memory merely as a medium for acceleration, without adequately considering the space overhead it introduces. This presents a critical challenge in real-world recommendation systems with billions of users, each of whom might initiate thousands of interactions and require massive memory for state storage. Fortunately, there have been several memory management strategies examined for compression in LLM, while most have not been evaluated on the recommendation task. To mitigate this gap, we introduce MALLOC, a comprehensive benchmark for memory-aware long sequence compression. MALLOC presents a comprehensive investigation and systematic classification of memory management techniques applicable to large sequential recommendations. These techniques are integrated into state-of-the-art recommenders, enabling a reproducible and accessible evaluation platform. Through extensive experiments across accuracy, efficiency, and complexity, we demonstrate the holistic reliability of MALLOC in advancing large-scale recommendation. Code is available at https://anonymous.4open.science/r/MALLOC.

Length-Adaptive Interest Network for Balancing Long and Short Sequence Modeling in CTR Prediction

User behavior sequences in modern recommendation systems exhibit significant length heterogeneity, ranging from sparse short-term interactions to rich long-term histories. While longer sequences provide more context, we observe that increasing the maximum input sequence length in existing CTR models paradoxically degrades performance for short-sequence users due to attention polarization and length imbalance in training data. To address this, we propose LAIN(Length-Adaptive Interest Network), a plug-and-play framework that explicitly incorporates sequence length as a conditioning signal to balance long- and short-sequence modeling. LAIN consists of three lightweight components: a Spectral Length Encoder that maps length into continuous representations, Length-Conditioned Prompting that injects global contextual cues into both long- and short-term behavior branches, and Length-Modulated Attention that adaptively adjusts attention sharpness based on sequence length. Extensive experiments on three real-world benchmarks across five strong CTR backbones show that LAIN consistently improves overall performance, achieving up to 1.15% AUC gain and 2.25% log loss reduction. Notably, our method significantly improves accuracy for short-sequence users without sacrificing longsequence effectiveness. Our work offers a general, efficient, and deployable solution to mitigate length-induced bias in sequential recommendation.

CollectiveKV: Decoupling and Sharing Collaborative Information in Sequential Recommendation

Sequential recommendation models are widely used in applications, yet they face stringent latency requirements. Mainstream models leverage the Transformer attention mechanism to improve performance, but its computational complexity grows with the sequence length, leading to a latency challenge for long sequences. Consequently, KV cache technology has recently been explored in sequential recommendation systems to reduce inference latency. However, KV cache introduces substantial storage overhead in sequential recommendation systems, which often have a large user base with potentially very long user history sequences. In this work, we observe that KV sequences across different users exhibit significant similarities, indicating the existence of collaborative signals in KV. Furthermore, we analyze the KV using singular value decomposition (SVD) and find that the information in KV can be divided into two parts: the majority of the information is shareable across users, while a small portion is user-specific. Motivated by this, we propose CollectiveKV, a cross-user KV sharing mechanism. It captures the information shared across users through a learnable global KV pool. During inference, each user retrieves high-dimensional shared KV from the pool and concatenates them with low-dimensional user-specific KV to obtain the final KV. Experiments on five sequential recommendation models and three datasets show that our method can compress the KV cache to only 0.8% of its original size, while maintaining or even enhancing model performance.

SSA3D: Text-Conditioned Assisted Self-Supervised Framework for Automatic Dental Abutment Design

Abutment design is a critical step in dental implant restoration. However, manual design involves tedious measurement and fitting, and research on automating this process with AI is limited, due to the unavailability of large annotated datasets. Although self-supervised learning (SSL) can alleviate data scarcity, its need for pre-training and fine-tuning results in high computational costs and long training times. In this paper, we propose a Self-supervised assisted automatic abutment design framework (SS$A^3$D), which employs a dual-branch architecture with a reconstruction branch and a regression branch. The reconstruction branch learns to restore masked intraoral scan data and transfers the learned structural information to the regression branch. The regression branch then predicts the abutment parameters under supervised learning, which eliminates the separate pre-training and fine-tuning process. We also design a Text-Conditioned Prompt (TCP) module to incorporate clinical information (such as implant location, system, and series) into SS$A^3$D. This guides the network to focus on relevant regions and constrains the parameter predictions. Extensive experiments on a collected dataset show that SS$A^3$D saves half of the training time and achieves higher accuracy than traditional SSL methods. It also achieves state-of-the-art performance compared to other methods, significantly improving the accuracy and efficiency of automated abutment design.

Fine-Tuning Vision-Language Models for Visual Navigation Assistance

We address vision-language-driven indoor navigation to assist visually impaired individuals in reaching a target location using images and natural language guidance. Traditional navigation systems are ineffective indoors due to the lack of precise location data. Our approach integrates vision and language models to generate step-by-step navigational instructions, enhancing accessibility and independence. We fine-tune the BLIP-2 model with Low Rank Adaptation (LoRA) on a manually annotated indoor navigation dataset. We propose an evaluation metric that refines the BERT F1 score by emphasizing directional and sequential variables, providing a more comprehensive measure of navigational performance. After applying LoRA, the model significantly improved in generating directional instructions, overcoming limitations in the original BLIP-2 model.

Hot-Swap MarkBoard: An Efficient Black-box Watermarking Approach for Large-scale Model Distribution

Recently, Deep Learning (DL) models have been increasingly deployed on end-user devices as On-Device AI, offering improved efficiency and privacy. However, this deployment trend poses more serious Intellectual Property (IP) risks, as models are distributed on numerous local devices, making them vulnerable to theft and redistribution. Most existing ownership protection solutions (e.g., backdoor-based watermarking) are designed for cloud-based AI-as-a-Service (AIaaS) and are not directly applicable to large-scale distribution scenarios, where each user-specific model instance must carry a unique watermark. These methods typically embed a fixed watermark, and modifying the embedded watermark requires retraining the model. To address these challenges, we propose Hot-Swap MarkBoard, an efficient watermarking method. It encodes user-specific $n$-bit binary signatures by independently embedding multiple watermarks into a multi-branch Low-Rank Adaptation (LoRA) module, enabling efficient watermark customization without retraining through branch swapping. A parameter obfuscation mechanism further entangles the watermark weights with those of the base model, preventing removal without degrading model performance. The method supports black-box verification and is compatible with various model architectures and DL tasks, including classification, image generation, and text generation. Extensive experiments across three types of tasks and six backbone models demonstrate our method's superior efficiency and adaptability compared to existing approaches, achieving 100\% verification accuracy.

Category-aware EEG image generation based on wavelet transform and contrast semantic loss

Reconstructing visual stimuli from EEG signals is a crucial step in realizing brain-computer interfaces. In this paper, we propose a transformer-based EEG signal encoder integrating the Discrete Wavelet Transform (DWT) and the gating mechanism. Guided by the feature alignment and category-aware fusion losses, this encoder is used to extract features related to visual stimuli from EEG signals. Subsequently, with the aid of a pre-trained diffusion model, these features are reconstructed into visual stimuli. To verify the effectiveness of the model, we conducted EEG-to-image generation and classification tasks using the THINGS-EEG dataset. To address the limitations of quantitative analysis at the semantic level, we combined WordNet-based classification and semantic similarity metrics to propose a novel semantic-based score, emphasizing the ability of our model to transfer neural activities into visual representations. Experimental results show that our model significantly improves semantic alignment and classification accuracy, which achieves a maximum single-subject accuracy of 43\%, outperforming other state-of-the-art methods. The source code and supplementary material is available at https://github.com/zes0v0inn/DWT_EEG_Reconstruction/tree/main.

GMSA: Enhancing Context Compression via Group Merging and Layer Semantic Alignment

Large language models (LLMs) have achieved impressive performance in a variety of natural language processing (NLP) tasks. However, when applied to long-context scenarios, they face two challenges, i.e., low computational efficiency and much redundant information. This paper introduces GMSA, a context compression framework based on the encoder-decoder architecture, which addresses these challenges by reducing input sequence length and redundant information. Structurally, GMSA has two key components: Group Merging and Layer Semantic Alignment (LSA). Group merging is used to effectively and efficiently extract summary vectors from the original context. Layer semantic alignment, on the other hand, aligns the high-level summary vectors with the low-level primary input semantics, thus bridging the semantic gap between different layers. In the training process, GMSA first learns soft tokens that contain complete semantics through autoencoder training. To furtherly adapt GMSA to downstream tasks, we propose Knowledge Extraction Fine-tuning (KEFT) to extract knowledge from the soft tokens for downstream tasks. We train GMSA by randomly sampling the compression rate for each sample in the dataset. Under this condition, GMSA not only significantly outperforms the traditional compression paradigm in context restoration but also achieves stable and significantly faster convergence with only a few encoder layers. In downstream question-answering (QA) tasks, GMSA can achieve approximately a 2x speedup in end-to-end inference while outperforming both the original input prompts and various state-of-the-art (SOTA) methods by a large margin.