Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference latency. Speculative decoding (SD) mitigates this through a guess-and-verify strategy, but existing training-free variants face trade-offs: retrieval-based drafts break when no exact match exists, while logits-based drafts lack structural guidance. We propose RACER (Retrieval-Augmented Contextual Rapid Speculative Decoding), a lightweight and training-free method that integrates retrieved exact patterns with logit-driven future cues. This unification supplies both reliable anchors and flexible extrapolation, yielding richer speculative drafts. Experiments on Spec-Bench, HumanEval, and MGSM-ZH demonstrate that RACER consistently accelerates inference, achieving more than 2× speedup over autoregressive decoding, and outperforms prior training-free methods, offering a scalable, plug-and-play solution for efficient LLM decoding. Our source code is available at https://github.com/hkr04/RACER.

In fine-grained sparse Mixture-of-Experts (MoE) models, a large pool of specialized experts replaces a small homogeneous set, shifting performance and throughput to be governed by inference-time expert activation. Yet most existing optimization recipes implicitly assume a fixed activation budget (e.g., a constant Top-k per layer), whose behavior in fine-grained MoEs is poorly understood. We first characterize runtime skipping strategies, quantifying the accuracy–efficiency trade-off of (i) uniform fixed activation and (ii) static layer-wise Top-k allocation found by search. Our analysis reveals that static skipping can already provide substantial throughput gains, but optimal static schedules vary significantly across models and routing mechanisms. We therefore introduce Adaptive Skipping with Entropy-Penalized Thresholding (ASET), a training-free policy that adapts token-level activation using router confidence and entropy while remaining within the model’s original budget. Across the fine-grained MoEs we study, static skipping policies yield 10–78% throughput gains with minimal performance degradation, including ≥10% improvement on DeepSeek-V3 without measurable loss. On the OLMoE testbed, ASET yields a Pareto frontier between average activation and task quality. Overall, these results identify expert skipping as a practical lever for faster fine-grained MoE inference, with adaptive activation helping when fixed budgets are too rigid.

Multimodal Large Language Models (MLLMs) excel in general tasks but struggle with specialized, structured cultural symbols. We introduce BoYaEval, the first comprehensive benchmark dedicated to deciphering diverse Ancient Chinese musical notations, including five types of ancient Chinese music notation systems. These systems utilize unique spatial layouts and specialized ideograms to encode pitch and intricate playing techniques. BoYaEval comprises 3,175 high-quality images across these notation styles and establishes a three-tier evaluation: Structural Parsing (symbol recognition), Instructional Translation (technique mapping), and Musical Reasoning (melody derivation). We evaluate 21 leading MLLMs. Results indicate that while models perform adequately in basic recognition, they fail in cross-system compositional logic, scoring only around 27% on reasoning tasks. BoYaEval highlights the limitations of current MLLMs in processing diverse spatial-symbolic dependencies, bridging the gap between ancient wisdom and modern AI for digitizing intangible cultural heritage. The BoYaEval benchmark is publicly available at https://huggingface.co/datasets/MYTH-Lab/BoYaEval.

Long-video understanding is bottlenecked by the high cost of processing massive visual tokens. Current reduction strategies often rely on static allocation or inefficient in-network selection that disrupts optimized attention kernels. In this paper, we introduce Vista-LLM, a decoupled framework for query-guided visual token pruning. By filtering redundancy prior to inference with minimal overhead, Vista-LLM ensures full compatibility with Flash Attention. Our method employs a coarse-to-fine pipeline: (1) Query-Guided Dynamic Budgeting for adaptive temporal allocation; (2) a lightweight Semantic Scout for fine-grained, query-specific selection; and (3) Structure-Aware Compensation to preserve global context. Extensive experiments on benchmarks like Video-MME and MLVU demonstrate a significantly improved Pareto frontier. Notably, on LLaVA-OneVision, Vista-LLM reduces visual tokens by 90% and accelerates inference while retaining over 98% of baseline performance on average, effectively filtering visual noise.

Early Long-context Document Visual Question Answering (DocVQA) methods struggle with preserving visual semantics or handling finite context windows. Conversely, recent RAG-based approaches suffer from “semantic gaps” and “structural disconnections” due to passive retrieval mechanisms that ignore logical dependencies. To address these challenges, we introduce TRACE (Traversal Retrieval-Augmented Chain of Evidence). By navigating a Bi-Layered Graph that encodes both physical adjacency and semantic relevance, TRACE transforms retrieval from static matching into adaptive evidence chain construction. Furthermore, we propose M5BookVQA, a benchmark designed to assess deep, multi-hop reasoning in books, addressing the limitations of existing datasets. Extensive experiments show that TRACE achieves an average accuracy improvement of 14.07% on M5BookVQA and exhibits robust generalization with a 13.38% gain across four established benchmarks. Our source code is available at https://github.com/shimurenhlq/TRACE.

Universal Information Extraction (UIE) has garnered significant attention due to its ability to address model explosion problems effectively. Extractive UIE can achieve strong performance using a relatively small model, making it widely adopted. Extractive UIEs generally rely on task instructions for different tasks, including single-target instructions and multiple-target instructions. Single-target instruction UIE enables the extraction of only one type of relation at a time, limiting its ability to model correlations between relations and thus restricting its capability to extract complex relations. While multiple-target instruction UIE allows for the extraction of multiple relations simultaneously, the inclusion of irrelevant relations introduces decision complexity and impacts extraction accuracy. Therefore, for multi-relation extraction, we propose LDNet, which incorporates multi-aspect relation modeling and a label drop mechanism. By assigning different relations to different levels for understanding and decision-making, we reduce decision confusion. Additionally, the label drop mechanism effectively mitigates the impact of irrelevant relations. Experiments show that LDNet outperforms or achieves competitive performance with state-of-the-art systems on 9 tasks, 33 datasets, in both single-modal and multi-modal, few-shot and zero-shot settings.

Symbolic music is represented in two distinct forms: two-dimensional, visually intuitive score images, and one-dimensional, standardized text annotation sequences. While large language models have shown extraordinary potential in music, current research has primarily focused on unimodal symbol sequence text. Existing general-domain visual language models still lack the ability of music notation understanding. Recognizing this gap, we propose NOTA, the first large-scale comprehensive multimodal music notation dataset. It consists of 1,019,237 records, from 3 regions of the world, and contains 3 tasks. Based on the dataset, we trained NotaGPT, a music notation visual large language model. Specifically, we involve a pre-alignment training phase for cross-modal alignment between the musical notes depicted in music score images and their textual representation in ABC notation. Subsequent training phases focus on foundational music information extraction, followed by training on music score notation analysis. Experimental results demonstrate that our NotaGPT-7B achieves significant improvement on music understanding, showcasing the effectiveness of NOTA and the training pipeline.

As a crucial method in prompt engineering, In-Context Learning (ICL) enhances the generalization and knowledge utilization capabilities of Large Language Models (LLMs) (Dong et al., 2024). However, the lengthy retrieved contexts and limited token throughput in autoregressive models significantly constrain reasoning speed. To address this challenge, we propose N-Gram Trie Speculative Decoding, a novel approach that leverages the overlap between context and model output. This method constructs an n-gram trie from the context to generate drafts, accelerating token generation for LLMs. We evaluate our approach on summarization, Retrieval-Augmented Generation (RAG), and context-based Question Answering (QA) tasks. Experimental results on Vicuna-7B, Llama2-7B-Chat, and Llama3-8B-Instruct demonstrate substantial speed improvements without compromising accuracy. Compared with various strong baselines, our method achieves the highest mean speedup, showcasing its effectiveness and efficiency.

Large language models (LLMs) have achieved remarkable success across diverse domains. However, their potential as effective language teachers—particularly in complex pedagogical scenarios like teaching Chinese as a second language—remains inadequately assessed. To address this gap, we propose the first pedagogical competence benchmark for LLMs, rigorously evaluating their performance against international standards for Chinese language teachers. Our framework spans three core dimensions: (1) basic knowledge evaluation, covering 32 subtopics across five major categories; (2) international teacher examination, based on data collected from international Chinese teacher certification exams; and (3) teaching practice evaluation, where target LLMs summarize knowledge points and design instructional content for student models, followed by testing the student models to assess the LLM’s ability to distill and teach key concepts.We conduct a comprehensive evaluation of 13 latest multilingual and Chinese LLMs. While most models demonstrate promising pedagogical potential, there remains substantial room for improvement in their teaching capabilities. This study contributes to the development of AI-assisted language education tools capable of rivaling human teaching excellence. The benchmark dataset and evaluation scripts used in this study are publicly available at https://github.com/Line-Kite/CLTE.

In-context learning (ICL) has emerged as a powerful paradigm for task adaptation in large language models (LLMs), where models infer underlying task structures from a few demonstrations. However, ICL remains susceptible to biases that arise from prior knowledge and contextual demonstrations, which can degrade the performance of LLMs. Existing bias calibration methods typically apply fixed class priors across all inputs, limiting their efficacy in dynamic ICL settings where the context for each query differs. To address these limitations, we adopt implicit sequential Bayesian inference as a framework for interpreting ICL, identify “surprise” as an informative signal for class prior shift, and introduce a novel method—Surprise Calibration (SC). SC leverages the notion of surprise to capture the temporal dynamics of class priors, providing a more adaptive and computationally efficient solution for in-context learning. We empirically demonstrate the superiority of SC over existing bias calibration techniques across a range of benchmark natural language processing tasks.

Large Language Models (LLMs) have achieved impressive accomplishments in recent years. However, the increasing memory consumption of KV cache has possessed a significant challenge to the inference system. Eviction methods have revealed the inherent redundancy within the KV cache, demonstrating its potential for reduction, particularly in deeper layers. However, KV cache reduction for shallower layers has been found to be insufficient. Based on our observation that, the KV cache exhibits a high degree of similarity. Based on this observation, we proposed a novel KV cache reduction method, SpindleKV, which balances both shallow and deep layers. For deep layers, we employ an attention weight based eviction method, while for shallow layers, we apply a codebook based replacement approach which is learnt by similarity and merging policy. Moreover, SpindleKV addressed the Grouped-Query Attention (GQA) dilemma faced by other attention based eviction methods. Experiments on two common benchmarks with three different LLMs shown that SpindleKV obtained better KV cache reduction effect compared to baseline methods, while preserving similar or even better model performance.

Large Language Models (LLMs) and Retrieval Augmented Generation (RAG) methods have demonstrated significant potential on tasks across multiple domains. However, ellipses and coreferences, as common phenomena in dialogue scenes, pose challenges to LLMs’ understanding and RAG’s retrieval accuracy. The previous works ignore the negative impact of this fuzzy data on RAG system.We explore the capabilities of LLMs and RAG systems in dialogue scenarios and use Incomplete Utterance Rewriting (IUR) to complete the key information in dialogue to enhance retrieval.Besides, we propose a lightweight IUR model for query rewriting. It is an end-to-end framework for node linking and iterative inference, incorporating two newly proposed probing semantic features derived from generative pre-training. This framework treats IUR as a series of link decisions on the input sequence and the incrementally constructed rewriting outputs.To test the performance of RAG system in the model multi-round dialogue scenario, we construct an RAG dialogue dataset on English and Chinese, Dialogue-RAG-MULTI-v1.0.Experiment results show that utterance rewriting can effectively improve the retrieval and generation ability of RAG system in dialogue scenes. Experiments on IUR tasks demonstrate the excellent performance of our lightweight IUR method.