MTServe: Efficient Serving for Generative Recommendation Models with Hierarchical Caches

Generative recommendation (GR) offers superior modeling capabilities but suffers from prohibitive inference costs due to the repeated encoding of long user histories. While cross-request Key-Value (KV) cache reuse presents a significant optimization opportunity, the massive scale of individual user states creates a storage explosion that far exceeds physical GPU limits. We propose MTServe, a hierarchical cache management system that virtualizes GPU memory by leveraging host RAM as a scalable backup store. To bridge the I/O gap between tiers, MTServe introduces a suite of system-level optimizations, including a hybrid storage layout, an asynchronous data transfer pipeline, and a locality-driven replacement policy. On both public and production datasets, MTServe delivers up to 3.1* speedup while maintaining near-perfect hit ratios (>98.5%).

Scheduling LLM Inference with Uncertainty-Aware Output Length Predictions

To schedule LLM inference, the \textit{shortest job first} (SJF) principle is favorable by prioritizing requests with short output lengths to avoid head-of-line (HOL) blocking. Existing methods usually predict a single output length for each request to facilitate scheduling. We argue that such a \textit{point estimate} does not match the \textit{stochastic} decoding process of LLM inference, where output length is \textit{uncertain} by nature and determined by when the end-of-sequence (EOS) token is sampled. Hence, the output length of each request should be fitted with a distribution rather than a single value. With an in-depth analysis of empirical data and the stochastic decoding process, we observe that output length follows a heavy-tailed distribution and can be fitted with the log-t distribution. On this basis, we propose a simple metric called Tail Inflated Expectation (TIE) to replace the output length in SJF scheduling, which adjusts the expectation of a log-t distribution with its tail probabilities to account for the risk that a request generates long outputs. To evaluate our TIE scheduler, we compare it with three strong baselines, and the results show that TIE reduces the per-token latency by $2.31\times$ for online inference and improves throughput by $1.42\times$ for offline data generation.

Visual Attention Drifts,but Anchors Hold:Mitigating Hallucination in Multimodal Large Language Models via Cross-Layer Visual Anchors

Multimodal Large Language Models often suffer from object hallucination. While existing research utilizes attention enhancement and visual retracing, we find these works lack sufficient interpretability regarding attention drift in final model stages. In this paper, we investigate the layer wise evolution of visual features and discover that hallucination stems from deep layer attention regressing toward initial visual noise from early layers. We observe that output reliability depends on acquiring visual anchors at intermediate layers rather than final layers. Based on these insights, we propose CLVA, which stands for Cross-Layer Visual Anchors, a training free method that reinforces critical mid layer features while suppressing regressive noise. This approach effectively pulls deep layer attention back to correct visual regions by utilizing essential anchors captured from attention dynamics. We evaluate our method across diverse architectures and benchmarks, demonstrating outstanding performance without significant increase in computational time and GPU memory.

AdaCultureSafe: Adaptive Cultural Safety Grounded by Cultural Knowledge in Large Language Models

With the widespread adoption of Large Language Models (LLMs), respecting indigenous cultures becomes essential for models' culturally safety and responsible global applications. Existing studies separately consider cultural safety and cultural knowledge and neglect that the former should be grounded by the latter. This severely prevents LLMs from yielding culture-specific respectful responses. Consequently, adaptive cultural safety remains a formidable task. In this work, we propose to jointly model cultural safety and knowledge. First and foremost, cultural-safety and knowledge-paired data serve as the key prerequisite to conduct this research. However, the cultural diversity across regions and the subtlety of cultural differences pose significant challenges to the creation of such paired evaluation data. To address this issue, we propose a novel framework that integrates authoritative cultural knowledge descriptions curation, LLM-automated query generation, and heavy manual verification. Accordingly, we obtain a dataset named AdaCultureSafe containing 4.8K manually decomposed fine-grained cultural descriptions and the corresponding 48K manually verified safety- and knowledge-oriented queries. Upon the constructed dataset, we evaluate three families of popular LLMs on their cultural safety and knowledge proficiency, via which we make a critical discovery: no significant correlation exists between their cultural safety and knowledge proficiency. We then delve into the utility-related neuron activations within LLMs to investigate the potential cause of the absence of correlation, which can be attributed to the difference of the objectives of pre-training and post-alignment. We finally present a knowledge-grounded method, which significantly enhances cultural safety by enforcing the integration of knowledge into the LLM response generation process.

Beyond Static Snapshots: Dynamic Modeling and Forecasting of Group-Level Value Evolution with Large Language Models

Social simulation is critical for mining complex social dynamics and supporting data-driven decision making. LLM-based methods have emerged as powerful tools for this task by leveraging human-like social questionnaire responses to model group behaviors. Existing LLM-based approaches predominantly focus on group-level values at discrete time points, treating them as static snapshots rather than dynamic processes. However, group-level values are not fixed but shaped by long-term social changes. Modeling their dynamics is thus crucial for accurate social evolution prediction--a key challenge in both data mining and social science. This problem remains underexplored due to limited longitudinal data, group heterogeneity, and intricate historical event impacts. To bridge this gap, we propose a novel framework for group-level dynamic social simulation by integrating historical value trajectories into LLM-based human response modeling. We select China and the U.S. as representative contexts, conducting stratified simulations across four core sociodemographic dimensions (gender, age, education, income). Using the World Values Survey, we construct a multi-wave, group-level longitudinal dataset to capture historical value evolution, and then propose the first event-based prediction method for this task, unifying social events, current value states, and group attributes into a single framework. Evaluations across five LLM families show substantial gains: a maximum 30.88\% improvement on seen questions and 33.97\% on unseen questions over the Vanilla baseline. We further find notable cross-group heterogeneity: U.S. groups are more volatile than Chinese groups, and younger groups in both countries are more sensitive to external changes. These findings advance LLM-based social simulation and provide new insights for social scientists to understand and predict social value changes.

End-to-End Semantic ID Generation for Generative Advertisement Recommendation

Generative Recommendation (GR) has excelled by framing recommendation as next-token prediction. This paradigm relies on Semantic IDs (SIDs) to tokenize large-scale items into discrete sequences. Existing GR approaches predominantly generate SIDs via Residual Quantization (RQ), where items are encoded into embeddings and then quantized to discrete SIDs. However, this paradigm suffers from inherent limitations: 1) Objective misalignment and semantic degradation stemming from the two-stage compression; 2) Error accumulation inherent in the structure of RQ. To address these limitations, we propose UniSID, a Unified SID generation framework for generative advertisement recommendation. Specifically, we jointly optimize embeddings and SIDs in an end-to-end manner from raw advertising data, enabling semantic information to flow directly into the SID space and thus addressing the inherent limitations of the two-stage cascading compression paradigm. To capture fine-grained semantics, a multi-granularity contrastive learning strategy is introduced to align distinct items across SID levels. Finally, a summary-based ad reconstruction mechanism is proposed to encourage SIDs to capture high-level semantic information that is not explicitly present in advertising contexts. Experiments demonstrate that UniSID consistently outperforms state-of-the-art SID generation methods, yielding up to a 4.62% improvement in Hit Rate metrics across downstream advertising scenarios compared to the strongest baseline.

Sparsity-Aware Unlearning for Large Language Models

Large Language Models (LLMs) inevitably memorize sensitive information during training, posing significant privacy risks. Machine unlearning has emerged as a promising solution to selectively remove such information without full retraining. However, existing methods are designed for dense models and overlook model sparsification-an essential technique for efficient LLM deployment. We find that unlearning effectiveness degrades substantially on sparse models. Through empirical analysis, we reveal that this degradation occurs because existing unlearning methods require updating all parameters, yet sparsification prunes substantial weights to zero, fundamentally limiting the model's forgetting capacity. To address this challenge, we propose Sparsity-Aware Unlearning (SAU), which decouples unlearning from sparsification objectives through gradient masking that redirects updates to surviving weights, combined with importance-aware redistribution to compensate for pruned parameters. Extensive experiments demonstrate that SAU significantly outperforms existing methods on sparse LLMs, achieving effective forgetting while preserving model utility.

Heaven-Sent or Hell-Bent? Benchmarking the Intelligence and Defectiveness of LLM Hallucinations

Hallucinations in large language models (LLMs) are commonly regarded as errors to be minimized. However, recent perspectives suggest that some hallucinations may encode creative or epistemically valuable content, a dimension that remains underquantified in current literature. Existing hallucination detection methods primarily focus on factual consistency, struggling to handle heterogeneous scientific tasks and balance creativity with accuracy. To address these challenges, we propose HIC-Bench, a novel evaluation framework that categorizes hallucinations into Intelligent Hallucinations (IH) and Defective Hallucinations (DH), enabling systematic investigation of their interplay in LLM creativity. HIC-Bench features three core characteristics: (1) Structured IH/DH Assessment. using a multi-dimensional metric matrix integrating Torrance Tests of Creative Thinking (TTCT) metrics (Originality, Feasibility, Value) with hallucination-specific dimensions (scientific plausibility, factual deviation); (2) Cross-Domain Applicability. spanning ten scientific domains with open-ended innovation tasks; and (3) Dynamic Prompt Optimization. leveraging the Dynamic Hallucination Prompt (DHP) to guide models toward creative and reliable outputs. The evaluation process employs multiple LLM judges, averaging scores to mitigate bias, with human annotators verifying IH/DH classifications. Experimental results reveal a nonlinear relationship between IH and DH, demonstrating that creativity and correctness can be jointly optimized. These insights position IH as a catalyst for creativity and reveal the ability of LLM hallucinations to drive scientific innovation.Additionally, the HIC-Bench offers a valuable platform for advancing research into the creative intelligence of LLM hallucinations.

REMISVFU: Vertical Federated Unlearning via Representation Misdirection for Intermediate Output Feature

Data-protection regulations such as the GDPR grant every participant in a federated system a right to be forgotten. Federated unlearning has therefore emerged as a research frontier, aiming to remove a specific party's contribution from the learned model while preserving the utility of the remaining parties. However, most unlearning techniques focus on Horizontal Federated Learning (HFL), where data are partitioned by samples. In contrast, Vertical Federated Learning (VFL) allows organizations that possess complementary feature spaces to train a joint model without sharing raw data. The resulting feature-partitioned architecture renders HFL-oriented unlearning methods ineffective. In this paper, we propose REMISVFU, a plug-and-play representation misdirection framework that enables fast, client-level unlearning in splitVFL systems. When a deletion request arrives, the forgetting party collapses its encoder output to a randomly sampled anchor on the unit sphere, severing the statistical link between its features and the global model. To maintain utility for the remaining parties, the server jointly optimizes a retention loss and a forgetting loss, aligning their gradients via orthogonal projection to eliminate destructive interference. Evaluations on public benchmarks show that REMISVFU suppresses back-door attack success to the natural class-prior level and sacrifices only about 2.5% points of clean accuracy, outperforming state-of-the-art baselines.

DevPiolt: Operation Recommendation for IoT Devices at Xiaomi Home

Operation recommendation for IoT devices refers to generating personalized device operations for users based on their context, such as historical operations, environment information, and device status. This task is crucial for enhancing user satisfaction and corporate profits. Existing recommendation models struggle with complex operation logic, diverse user preferences, and sensitive to suboptimal suggestions, limiting their applicability to IoT device operations. To address these issues, we propose DevPiolt, a LLM-based recommendation model for IoT device operations. Specifically, we first equip the LLM with fundamental domain knowledge of IoT operations via continual pre-training and multi-task fine-tuning. Then, we employ direct preference optimization to align the fine-tuned LLM with specific user preferences. Finally, we design a confidence-based exposure control mechanism to avoid negative user experiences from low-quality recommendations. Extensive experiments show that DevPiolt significantly outperforms baselines on all datasets, with an average improvement of 69.5% across all metrics. DevPiolt has been practically deployed in Xiaomi Home app for one quarter, providing daily operation recommendations to 255,000 users. Online experiment results indicate a 21.6% increase in unique visitor device coverage and a 29.1% increase in page view acceptance rates.