arXiv subjects

Qianhui Wu

Publications and source records attributed to Qianhui Wu.

35 records · Page 2Linked to original sources

arXiv2025

MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention

The integration of long-context capabilities with visual understanding unlocks unprecedented potential for Vision Language Models (VLMs). However, the quadratic attention complexity during the pre-filling phase remains a significant obstacle to real-world deployment. To overcome this limitation, we introduce MMInference (Multimodality Million tokens Inference), a dynamic sparse attention method that accelerates the prefilling stage for long-context multi-modal inputs. First, our analysis reveals that the temporal and spatial locality of video input leads to a unique sparse pattern, the Grid pattern. Simultaneously, VLMs exhibit markedly different sparse distributions across different modalities. We introduce a permutation-based method to leverage the unique Grid pattern and handle modality boundary issues. By offline search the optimal sparse patterns for each head, MMInference constructs the sparse distribution dynamically based on the input. We also provide optimized GPU kernels for efficient sparse computations. Notably, MMInference integrates seamlessly into existing VLM pipelines without any model modifications or fine-tuning. Experiments on multi-modal benchmarks-including Video QA, Captioning, VisionNIAH, and Mixed-Modality NIAH-with state-of-the-art long-context VLMs (LongVila, LlavaVideo, VideoChat-Flash, Qwen2.5-VL) show that MMInference accelerates the pre-filling stage by up to 8.3x at 1M tokens while maintaining accuracy. Our code is available at https://aka.ms/MMInference.

cs.CV↗

arXiv2025

SCBench: A KV Cache-Centric Analysis of Long-Context Methods

Long-context LLMs have enabled numerous downstream applications but also introduced significant challenges related to computational and memory efficiency. To address these challenges, optimizations for long-context inference have been developed, centered around the KV cache. However, existing benchmarks often evaluate in single-request, neglecting the full lifecycle of the KV cache in real-world use. This oversight is particularly critical, as KV cache reuse has become widely adopted in LLMs inference frameworks, such as vLLM and SGLang, as well as by LLM providers, including OpenAI, Microsoft, Google, and Anthropic. To address this gap, we introduce SCBench(SharedContextBench), a comprehensive benchmark for evaluating long-context methods from a KV cachecentric perspective: 1) KV cache generation, 2) KV cache compression, 3) KV cache retrieval, 4) KV cache loading. Specifically, SCBench uses test examples with shared context, ranging 12 tasks with two shared context modes, covering four categories of long-context capabilities: string retrieval, semantic retrieval, global information, and multi-task. With it, we provide an extensive KV cache-centric analysis of eight categories long-context solutions, including Gated Linear RNNs, Mamba-Attention hybrids, and efficient methods such as sparse attention, KV cache dropping, quantization, retrieval, loading, and prompt compression. The evaluation is conducted on 8 long-context LLMs. Our findings show that sub-O(n) memory methods suffer in multi-turn scenarios, while sparse encoding with O(n) memory and sub-O(n^2) pre-filling computation perform robustly. Dynamic sparsity yields more expressive KV caches than static patterns, and layer-level sparsity in hybrid architectures reduces memory usage with strong performance. Additionally, we identify attention distribution shift issues in long-generation scenarios. https://aka.ms/SCBench.

cs.CL↗

arXiv2025

On Memory Construction and Retrieval for Personalized Conversational Agents

To deliver coherent and personalized experiences in long-term conversations, existing approaches typically perform retrieval augmented response generation by constructing memory banks from conversation history at either the turn-level, session-level, or through summarization techniques.In this paper, we present two key findings: (1) The granularity of memory unit matters: turn-level, session-level, and summarization-based methods each exhibit limitations in both memory retrieval accuracy and the semantic quality of the retrieved content. (2) Prompt compression methods, such as LLMLingua-2, can effectively serve as a denoising mechanism, enhancing memory retrieval accuracy across different granularities. Building on these insights, we propose SeCom, a method that constructs the memory bank at segment level by introducing a conversation segmentation model that partitions long-term conversations into topically coherent segments, while applying compression based denoising on memory units to enhance memory retrieval. Experimental results show that SeCom exhibits a significant performance advantage over baselines on long-term conversation benchmarks LOCOMO and Long-MT-Bench+. Additionally, the proposed conversation segmentation method demonstrates superior performance on dialogue segmentation datasets such as DialSeg711, TIAGE, and SuperDialSeg.

cs.CL↗

arXiv2025

Magma: A Foundation Model for Multimodal AI Agents

We present Magma, a foundation model that serves multimodal AI agentic tasks in both the digital and physical worlds. Magma is a significant extension of vision-language (VL) models in that it not only retains the VL understanding ability (verbal intelligence) of the latter, but is also equipped with the ability to plan and act in the visual-spatial world (spatial-temporal intelligence) and complete agentic tasks ranging from UI navigation to robot manipulation. To endow the agentic capabilities, Magma is pretrained on large amounts of heterogeneous datasets spanning from images, videos to robotics data, where the actionable visual objects (e.g., clickable buttons in GUI) in images are labeled by Set-of-Mark (SoM) for action grounding, and the object movements (e.g., the trace of human hands or robotic arms) in videos are labeled by Trace-of-Mark (ToM) for action planning. Extensive experiments show that SoM and ToM reach great synergy and facilitate the acquisition of spatial-temporal intelligence for our Magma model, which is fundamental to a wide range of tasks as shown in Fig.1. In particular, Magma creates new state-of-the-art results on UI navigation and robotic manipulation tasks, outperforming previous models that are specifically tailored to these tasks. On image and video-related multimodal tasks, Magma also compares favorably to popular large multimodal models that are trained on much larger datasets. We make our model and code public for reproducibility at https://microsoft.github.io/Magma.

cs.CV↗

arXiv2024

TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning

The increasing prevalence of large language models (LLMs) such as GPT-4 in various applications has led to a surge in the size of prompts required for optimal performance, leading to challenges in computational efficiency. Prompt compression aims to reduce the inference cost by minimizing input tokens without compromising on the task performance. However, existing prompt compression techniques either rely on sub-optimal metrics such as information entropy or model it as a task-agnostic token classification problem that fails to capture task-specific information. To address these issues, we propose a novel and efficient reinforcement learning (RL) based task-aware prompt compression method. To ensure low latency requirements, we leverage existing Transformer encoder-based token classification model while guiding the learning process with task-specific reward signals using lightweight REINFORCE algorithm. We evaluate the performance of our method on three diverse and challenging tasks including text summarization, question answering and code summarization. We demonstrate that our RL-guided compression method improves the task performance by 8% - 189% across these three scenarios over state-of-the-art compression techniques while satisfying the same compression rate and latency requirements.

cs.CL↗

arXiv2024

MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention

The computational challenges of Large Language Model (LLM) inference remain a significant barrier to their widespread deployment, especially as prompt lengths continue to increase. Due to the quadratic complexity of the attention computation, it takes 30 minutes for an 8B LLM to process a prompt of 1M tokens (i.e., the pre-filling stage) on a single A100 GPU. Existing methods for speeding up prefilling often fail to maintain acceptable accuracy or efficiency when applied to long-context LLMs. To address this gap, we introduce MInference (Milliontokens Inference), a sparse calculation method designed to accelerate pre-filling of long-sequence processing. Specifically, we identify three unique patterns in long-context attention matrices-the A-shape, Vertical-Slash, and Block-Sparsethat can be leveraged for efficient sparse computation on GPUs. We determine the optimal pattern for each attention head offline and dynamically build sparse indices based on the assigned pattern during inference. With the pattern and sparse indices, we perform efficient sparse attention calculations via our optimized GPU kernels to significantly reduce the latency in the pre-filling stage of long-context LLMs. Our proposed technique can be directly applied to existing LLMs without any modifications to the pre-training setup or additional fine-tuning. By evaluating on a wide range of downstream tasks, including InfiniteBench, RULER, PG-19, and Needle In A Haystack, and models including LLaMA-3-1M, GLM4-1M, Yi-200K, Phi-3-128K, and Qwen2-128K, we demonstrate that MInference effectively reduces inference latency by up to 10x for pre-filling on an A100, while maintaining accuracy. Our code is available at https://aka.ms/MInference.

cs.CL↗

arXiv2024

LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression

In long context scenarios, large language models (LLMs) face three main challenges: higher computational cost, performance reduction, and position bias. Research indicates that LLM performance hinges on the density and position of key information in the input prompt. Inspired by these findings, we propose LongLLMLingua for prompt compression towards improving LLMs' perception of the key information to simultaneously address the three challenges. Our extensive evaluation across various long context scenarios demonstrates that LongLLMLingua not only enhances performance but also significantly reduces costs and latency. For instance, in the NaturalQuestions benchmark, LongLLMLingua boosts performance by up to 21.4% with around 4x fewer tokens in GPT-3.5-Turbo, leading to substantial cost savings. It achieves a 94.0% cost reduction in the LooGLE benchmark. Moreover, when compressing prompts of about 10k tokens at ratios of 2x-6x, LongLLMLingua can accelerate end-to-end latency by 1.4x-2.6x. Our code is available at https://aka.ms/LongLLMLingua.

cs.CL↗

arXiv2024

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

This paper focuses on task-agnostic prompt compression for better generalizability and efficiency. Considering the redundancy in natural language, existing approaches compress prompts by removing tokens or lexical units according to their information entropy obtained from a causal language model such as LLaMa-7B. The challenge is that information entropy may be a suboptimal compression metric: (i) it only leverages unidirectional context and may fail to capture all essential information needed for prompt compression; (ii) it is not aligned with the prompt compression objective. To address these issues, we propose a data distillation procedure to derive knowledge from an LLM to compress prompts without losing crucial information, and meantime, introduce an extractive text compression dataset. We formulate prompt compression as a token classification problem to guarantee the faithfulness of the compressed prompt to the original one, and use a Transformer encoder as the base architecture to capture all essential information for prompt compression from the full bidirectional context. Our approach leads to lower latency by explicitly learning the compression objective with smaller models such as XLM-RoBERTa-large and mBERT. We evaluate our method on both in-domain and out-of-domain datasets, including MeetingBank, LongBench, ZeroScrolls, GSM8K, and BBH. Despite its small size, our model shows significant performance gains over strong baselines and demonstrates robust generalization ability across different LLMs. Additionally, our model is 3x-6x faster than existing prompt compression methods, while accelerating the end-to-end latency by 1.6x-2.9x with compression ratios of 2x-5x. Our code is available at https://aka.ms/LLMLingua-2.

cs.CL↗

arXiv2023

LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models

Large language models (LLMs) have been applied in various applications due to their astonishing capabilities. With advancements in technologies such as chain-of-thought (CoT) prompting and in-context learning (ICL), the prompts fed to LLMs are becoming increasingly lengthy, even exceeding tens of thousands of tokens. To accelerate model inference and reduce cost, this paper presents LLMLingua, a coarse-to-fine prompt compression method that involves a budget controller to maintain semantic integrity under high compression ratios, a token-level iterative compression algorithm to better model the interdependence between compressed contents, and an instruction tuning based method for distribution alignment between language models. We conduct experiments and analysis over four datasets from different scenarios, i.e., GSM8K, BBH, ShareGPT, and Arxiv-March23; showing that the proposed approach yields state-of-the-art performance and allows for up to 20x compression with little performance loss. Our code is available at https://aka.ms/LLMLingua.

cs.CL↗

arXiv2023

LafitE: Latent Diffusion Model with Feature Editing for Unsupervised Multi-class Anomaly Detection

In the context of flexible manufacturing systems that are required to produce different types and quantities of products with minimal reconfiguration, this paper addresses the problem of unsupervised multi-class anomaly detection: develop a unified model to detect anomalies from objects belonging to multiple classes when only normal data is accessible. We first explore the generative-based approach and investigate latent diffusion models for reconstruction to mitigate the notorious ``identity shortcut'' issue in auto-encoder based methods. We then introduce a feature editing strategy that modifies the input feature space of the diffusion model to further alleviate ``identity shortcuts'' and meanwhile improve the reconstruction quality of normal regions, leading to fewer false positive predictions. Moreover, we are the first who pose the problem of hyperparameter selection in unsupervised anomaly detection, and propose a solution of synthesizing anomaly data for a pseudo validation set to address this problem. Extensive experiments on benchmark datasets MVTec-AD and MPDD show that the proposed LafitE, \ie, Latent Diffusion Model with Feature Editing, outperforms state-of-art methods by a significant margin in terms of average AUROC. The hyperparamters selected via our pseudo validation set are well-matched to the real test set.

cs.CV↗

arXiv2023

Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text

Self-supervised representation learning has proved to be a valuable component for out-of-distribution (OoD) detection with only the texts of in-distribution (ID) examples. These approaches either train a language model from scratch or fine-tune a pre-trained language model using ID examples, and then take the perplexity output by the language model as OoD scores. In this paper, we analyze the complementary characteristics of both OoD detection methods and propose a multi-level knowledge distillation approach that integrates their strengths while mitigating their limitations. Specifically, we use a fine-tuned model as the teacher to teach a randomly initialized student model on the ID examples. Besides the prediction layer distillation, we present a similarity-based intermediate layer distillation method to thoroughly explore the representation space of the teacher model. In this way, the learned student can better represent the ID data manifold while gaining a stronger ability to map OoD examples outside the ID data manifold with the regularization inherited from pre-training. Besides, the student model sees only ID examples during parameter learning, further promoting more distinguishable features for OoD detection. We conduct extensive experiments over multiple benchmark datasets, i.e., CLINC150, SST, ROSTD, 20 NewsGroups, and AG News; showing that the proposed method yields new state-of-the-art performance. We also explore its application as an AIGC detector to distinguish between answers generated by ChatGPT and human experts. It is observed that our model exceeds human evaluators in the pair-expert task on the Human ChatGPT Comparison Corpus.

cs.CL↗

arXiv2023

CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity Recognition

Cross-lingual named entity recognition (NER) aims to train an NER system that generalizes well to a target language by leveraging labeled data in a given source language. Previous work alleviates the data scarcity problem by translating source-language labeled data or performing knowledge distillation on target-language unlabeled data. However, these methods may suffer from label noise due to the automatic labeling process. In this paper, we propose CoLaDa, a Collaborative Label Denoising Framework, to address this problem. Specifically, we first explore a model-collaboration-based denoising scheme that enables models trained on different data sources to collaboratively denoise pseudo labels used by each other. We then present an instance-collaboration-based strategy that considers the label consistency of each token's neighborhood in the representation space for denoising. Experiments on different benchmark datasets show that the proposed CoLaDa achieves superior results compared to previous methods, especially when generalizing to distant languages.

cs.CL↗

arXiv2022

Decomposed Meta-Learning for Few-Shot Named Entity Recognition

Few-shot named entity recognition (NER) systems aim at recognizing novel-class named entities based on only a few labeled examples. In this paper, we present a decomposed meta-learning approach which addresses the problem of few-shot NER by sequentially tackling few-shot span detection and few-shot entity typing using meta-learning. In particular, we take the few-shot span detection as a sequence labeling problem and train the span detector by introducing the model-agnostic meta-learning (MAML) algorithm to find a good model parameter initialization that could fast adapt to new entity classes. For few-shot entity typing, we propose MAML-ProtoNet, i.e., MAML-enhanced prototypical networks to find a good embedding space that can better distinguish text span representations from different entity classes. Extensive experiments on various benchmarks show that our approach achieves superior performance over prior methods.

cs.CL↗

arXiv2021

AdvPicker: Effectively Leveraging Unlabeled Data via Adversarial Discriminator for Cross-Lingual NER

Neural methods have been shown to achieve high performance in Named Entity Recognition (NER), but rely on costly high-quality labeled data for training, which is not always available across languages. While previous works have shown that unlabeled data in a target language can be used to improve cross-lingual model performance, we propose a novel adversarial approach (AdvPicker) to better leverage such data and further improve results. We design an adversarial learning framework in which an encoder learns entity domain knowledge from labeled source-language data and better shared features are captured via adversarial training - where a discriminator selects less language-dependent target-language data via similarity to the source language. Experimental results on standard benchmark datasets well demonstrate that the proposed method benefits strongly from this data selection process and outperforms existing state-of-the-art methods; without requiring any additional external resources (e.g., gazetteers or via machine translation). The code is available at https://aka.ms/AdvPicker

cs.CL↗

arXiv2020

Enhanced Meta-Learning for Cross-lingual Named Entity Recognition with Minimal Resources

For languages with no annotated resources, transferring knowledge from rich-resource languages is an effective solution for named entity recognition (NER). While all existing methods directly transfer from source-learned model to a target language, in this paper, we propose to fine-tune the learned model with a few similar examples given a test case, which could benefit the prediction by leveraging the structural and semantic information conveyed in such similar examples. To this end, we present a meta-learning algorithm to find a good model parameter initialization that could fast adapt to the given test case and propose to construct multiple pseudo-NER tasks for meta-training by computing sentence similarities. To further improve the model's generalization ability across different languages, we introduce a masking scheme and augment the loss function with an additional maximum term during meta-training. We conduct extensive experiments on cross-lingual named entity recognition with minimal resources over five target languages. The results show that our approach significantly outperforms existing state-of-the-art methods across the board.

cs.CL↗

arXiv2020

Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language

To better tackle the named entity recognition (NER) problem on languages with little/no labeled data, cross-lingual NER must effectively leverage knowledge learned from source languages with rich labeled data. Previous works on cross-lingual NER are mostly based on label projection with pairwise texts or direct model transfer. However, such methods either are not applicable if the labeled data in the source languages is unavailable, or do not leverage information contained in unlabeled data in the target language. In this paper, we propose a teacher-student learning method to address such limitations, where NER models in the source languages are used as teachers to train a student model on unlabeled data in the target language. The proposed method works for both single-source and multi-source cross-lingual NER. For the latter, we further propose a similarity measuring method to better weight the supervision from different teacher models. Extensive experiments for 3 target languages on benchmark datasets well demonstrate that our method outperforms existing state-of-the-art methods for both single-source and multi-source cross-lingual NER.

cs.CL↗

arXiv2020

UniTrans: Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data

Prior works in cross-lingual named entity recognition (NER) with no/little labeled data fall into two primary categories: model transfer based and data transfer based methods. In this paper we find that both method types can complement each other, in the sense that, the former can exploit context information via language-independent features but sees no task-specific information in the target language; while the latter generally generates pseudo target-language training data via translation but its exploitation of context information is weakened by inaccurate translations. Moreover, prior works rarely leverage unlabeled data in the target language, which can be effortlessly collected and potentially contains valuable information for improved results. To handle both problems, we propose a novel approach termed UniTrans to Unify both model and data Transfer for cross-lingual NER, and furthermore, to leverage the available information from unlabeled target-language data via enhanced knowledge distillation. We evaluate our proposed UniTrans over 4 target languages on benchmark datasets. Our experimental results show that it substantially outperforms the existing state-of-the-art methods.

cs.CL↗