Search Results for author:
Found 574 papers, 283 papers with code
HW-TSC’s Participation at WMT 2021 Quality Estimation Shared Task
This paper presents our work in WMT 2021 Quality Estimation (QE) Shared Task.
HW-TSC’s Participation in the WMT 2021 Triangular MT Shared Task
This paper presents the submission of Huawei Translation Service Center (HW-TSC) to WMT 2021 Triangular MT Shared Task.
HW-TSC’s Participation in the WMT 2021 Large-Scale Multilingual Translation Task
This paper presents the submission of Huawei Translation Services Center (HW-TSC) to the WMT 2021 Large-Scale Multilingual Translation Task.
HW-TSC’s Submissions to the WMT21 Biomedical Translation Task
This paper describes the submission of Huawei Translation Service Center (HW-TSC) to WMT21 biomedical translation task in two language pairs: Chinese↔English and German↔English (Our registered team name is HuaweiTSC).
Modeling Intra- and Inter-Modal Relations: Hierarchical Graph Contrastive Learning for Multimodal Sentiment Analysis
This essentially allows the framework to understand the appropriate graph structures for learning intricate relations among different modalities.
HI-CMLM: Improve CMLM with Hybrid Decoder Input
Mask-predict CMLM (Ghazvininejad et al., 2019) has achieved stunning performance among non-autoregressive NMT models, but we find that the mechanism of predicting all of the target words only depending on the hidden state of [MASK] is not effective and efficient in initial iterations of refinement, resulting in ungrammatical repetitions and slow convergence.
Make the Blind Translator See The World: A Novel Transfer Learning Solution for Multimodal Machine Translation
Based on large-scale pretrained networks and the liability to be easily overfitting with limited labelled training data of multimodal translation (MMT) is a critical issue in MMT.
HW-TSC’s Participation in the WMT 2021 News Translation Shared Task
This paper presents the submission of Huawei Translate Services Center (HW-TSC) to the WMT 2021 News Translation Shared Task.
DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset
This paper describes in detail the construction process and data statistics of DuSQL.
Speaker-Aware Discourse Parsing on Multi-Party Dialogues
It is believed that speaker interactions are helpful for this task.
Ranked #2 on
Discourse Parsing
on STAC
Towards Robust Neural Machine Translation with Iterative Scheduled Data-Switch Training
Most existing methods on robust neural machine translation (NMT) construct adversarial examples by injecting noise into authentic examples and indiscriminately exploit two types of examples.
Prediction Difference Regularization against Perturbation for Neural Machine Translation
Regularization methods applying input perturbation have drawn considerable attention and have been frequently explored for NMT tasks in recent years.
RST Discourse Parsing with Second-Stage EDU-Level Pre-training
Pre-trained language models (PLMs) have shown great potentials in natural language processing (NLP) including rhetorical structure theory (RST) discourse parsing. Current PLMs are obtained by sentence-level pre-training, which is different from the basic processing unit, i. e. element discourse unit (EDU). To this end, we propose a second-stage EDU-level pre-training approach in this work, which presents two novel tasks to learn effective EDU representations continually based on well pre-trained language models. Concretely, the two tasks are (1) next EDU prediction (NEP) and (2) discourse marker prediction (DMP). We take a state-of-the-art transition-based neural parser as baseline, and adopt it with a light bi-gram EDU modification to effectively explore the EDU-level pre-trained EDU representation. Experimental results on a benckmark dataset show that our method is highly effective, leading a 2. 1-point improvement in F1-score. All codes and pre-trained models will be released publicly to facilitate future studies.
Semi-supervised Domain Adaptation for Dependency Parsing with Dynamic Matching Network
To address this issue, we for the first time apply a dynamic matching network on the shared-private model for semi-supervised cross-domain dependency parsing.
Synchronous Refinement for Neural Machine Translation
Machine translation typically adopts an encoder-to-decoder framework, in which the decoder generates the target sentence word-by-word in an auto-regressive manner.
Capture Human Disagreement Distributions by Calibrated Networks for Natural Language Inference
Natural Language Inference (NLI) datasets contain examples with highly ambiguous labels due to its subjectivity.
The HW-TSC’s Offline Speech Translation System for IWSLT 2022 Evaluation
For machine translation part, we pretrained three translation models on WMT21 dataset and fine-tuned them on in-domain corpora.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
How Length Prediction Influence the Performance of Non-Autoregressive Translation?
Length prediction is a special task in a series of NAT models where target length has to be determined before generation.
Joint Multi-modal Aspect-Sentiment Analysis with Auxiliary Cross-modal Relation Detection
Therefore, in this paper, we are the first to jointly perform multi-modal ATE (MATE) and multi-modal ASC (MASC), and we propose a multi-modal joint learning approach with auxiliary cross-modal relation detection for multi-modal aspect-level sentiment analysis (MALSA).
Encouraging Lexical Translation Consistency for Document-Level Neural Machine Translation
In this paper we apply “one translation per discourse” in NMT, and aim to encourage lexical translation consistency for document-level NMT.
数据标注方法比较研究:以依存句法树标注为例(Comparison Study on Data Annotation Approaches: Dependency Tree Annotation as Case Study)
“数据标注最重要的考虑因素是数据的质量和标注代价。我们调研发现自然语言处理领域的数据标注工作通常采用机标人校的标注方法以降低代价;同时, 很少有工作严格对比不同标注方法, 以探讨标注方法对标注质量和代价的影响。该文借助一个成熟的标注团队, 以依存句法数据标注为案例, 实验对比了机标人校、双人独立标注、及本文通过融合前两种方法所新提出的人机独立标注方法, 得到了一些初步的结论。”
A Coarse-to-Fine Labeling Framework for Joint Word Segmentation, POS Tagging, and Constituent Parsing
In the coarse labeling stage, the joint model outputs a bracketed tree, in which each node corresponds to one of four labels (i. e., phrase, subphrase, word, subword).
Bridging the Gap between Training and Inference: Multi-Candidate Optimization for Diverse Neural Machine Translation
Diverse NMT aims at generating multiple diverse yet faithful translations given a source sentence.
The HW-TSC’s Speech to Speech Translation System for IWSLT 2022 Evaluation
The paper presents the HW-TSC’s pipeline and results of Offline Speech to Speech Translation for IWSLT 2022.
HW-TSC at SemEval-2022 Task 3: A Unified Approach Fine-tuned on Multilingual Pretrained Model for PreTENS
In order to verify whether our model could also perform better in subtask 2 (the regression subtask), the ranking score is transformed into classification labels by an up-sampling strategy.
HW-TSC at SemEval-2022 Task 7: Ensemble Model Based on Pretrained Models for Identifying Plausible Clarifications
This paper describes the system for the identifying Plausible Clarifications of Implicit and Underspecified Phrases.
Stacked AMR Parsing with Silver Data
In particular, one recent seq-to-seq work directly fine-tunes AMR graph sequences on the encoder-decoder pre-trained language model and achieves new state-of-the-art results, outperforming previous works by a large margin.
APGN: Adversarial and Parameter Generation Networks for Multi-Source Cross-Domain Dependency Parsing
Thanks to the strong representation learning capability of deep learning, especially pre-training techniques with language model loss, dependency parsing has achieved great performance boost in the in-domain scenario with abundant labeled training data for target domains.
AniMaker: Automated Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation
Despite rapid advancements in video generation models, generating coherent storytelling videos that span multiple scenes and characters remains challenging.
Omni-DPO: A Dual-Perspective Paradigm for Dynamic Preference Learning of LLMs
However, existing DPO-based approaches typically treat all preference pairs uniformly, ignoring critical variations in their inherent quality and learning utility, leading to suboptimal data utilization and performance.
ComfyUI-R1: Exploring Reasoning Models for Workflow Generation
Starting with our curated dataset of 4K workflows, we construct long chain-of-thought (CoT) reasoning data, including node selection, workflow planning, and code-level workflow representation.
ComfyUI-Copilot: An Intelligent Assistant for Automated Workflow Development
We introduce ComfyUI-Copilot, a large language model-powered plugin designed to enhance the usability and efficiency of ComfyUI, an open-source platform for AI-driven art creation.
Small Stickers, Big Meanings: A Multilingual Sticker Semantic Understanding Dataset with a Gamified Approach
Stickers, though small, are a highly condensed form of visual expression, ubiquitous across messaging platforms and embraced by diverse cultures, genders, and age groups.
SplitLoRA: Balancing Stability and Plasticity in Continual Learning Through Gradient Space Splitting
Informed by this analysis, we then introduce an effective method that derives the optimal partition of the gradient space for previously learned tasks.
Adaptive Detoxification: Safeguarding General Capabilities of LLMs through Toxicity-Aware Knowledge Editing
Experimental results on multiple LLMs demonstrate that our ToxEdit outperforms previous state-of-the-art methods in both detoxification performance and safeguarding general capabilities of LLMs.
AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
The emergence of agentic recommender systems powered by Large Language Models (LLMs) represents a paradigm shift in personalized recommendations, leveraging LLMs' advanced reasoning and role-playing capabilities to enable autonomous, adaptive decision-making.
REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Large Reasoning Models
Meanwhile, online reinforcement learning mainly adopts a length reward to encourage short reasoning responses, but tends to lose the reflection ability and harm the performance.
VerIPO: Cultivating Long Reasoning in Video-LLMs via Verifier-Gudied Iterative Policy Optimization
Applying Reinforcement Learning (RL) to Video Large Language Models (Video-LLMs) shows significant promise for complex video reasoning.
Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer
Recognizing that different task vector subspaces contribute variably to model performance, we introduce a novel method called Neural Parameter Search (NPS-Pruning) for slimming down fine-tuned models.
Knowledge Grafting of Large Language Models
The resulting SkillPack serves as a compact and transferable knowledge carrier, ideal for heterogeneous model fusion and continual learning.
MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming
In the adversarial iterative optimization stage, the red-team model and the target model continuously improve their respective capabilities in interaction.
Dynamic Sampling that Adapts: Iterative DPO for Self-Aware Mathematical Reasoning
In the realm of data selection for reasoning tasks, existing approaches predominantly rely on externally predefined static metrics such as difficulty and diversity, which are often designed for supervised fine-tuning (SFT) and lack adaptability to continuous training processes.
GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI Agent
GUI automation faces critical challenges in dynamic environments.
Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors
By subtracting the machine-like patterns from the human-like distribution during the decoding process, CoPA is able to produce sentences that are less discernible by text detectors.
SynDec: A Synthesize-then-Decode Approach for Arbitrary Textual Style Transfer via Large Language Models
Large Language Models (LLMs) are emerging as dominant forces for textual style transfer.
Efficient Speech Language Modeling via Energy Distance in Continuous Latent Space
We introduce SLED, an alternative approach to speech language modeling by encoding speech waveforms into sequences of continuous latent representations and modeling them autoregressively using an energy distance objective.
Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification
The success of these methods relies on the alignment between draft candidates and the sampled outputs of the target model.
Towards DS-NER: Unveiling and Addressing Latent Noise in Distant Annotations
Distantly supervised named entity recognition (DS-NER) has emerged as a cheap and convenient alternative to traditional human annotation methods, enabling the automatic generation of training data by aligning text with external resources.
Accurate KV Cache Quantization with Outlier Tokens Tracing
KV Cache quantization presents a promising solution, striking a good balance between memory usage and accuracy.
Learning from Peers in Reasoning Models
Notably, our fine-tuned LeaP-T-7B matches the performance of DeepSeek-R1-Distill-Qwen-14B on AIME 2024.
Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models
Large Multimodal Reasoning Models (LMRMs) have emerged as a promising paradigm, integrating modalities such as text, images, audio, and video to support complex reasoning capabilities and aiming to achieve comprehensive perception, precise understanding, and deep reasoning.
CountDiffusion: Text-to-Image Synthesis with Training-Free Counting-Guidance Diffusion
Stable Diffusion has advanced text-to-image synthesis, but training models to generate images with accurate object quantity is still difficult due to the high computational cost and the challenge of teaching models the abstract concept of quantity.
A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law
This survey explores recent advancements in reasoning large language models (LLMs) designed to mimic "slow thinking" - a reasoning process inspired by human cognition, as described in Kahneman's Thinking, Fast and Slow.
Taming the Titans: A Survey of Efficient LLM Inference Serving
Finally, we outline potential research directions to further advance the field of LLM inference serving.
Efficient Reasoning for LLMs through Speculative Chain-of-Thought
The proposed thinking behavior alignment improves the efficiency of drafting and the draft selection strategy maintains the prediction accuracy for complex problems.
VideoVista-CulturalLingo: 360$^\circ$ Horizons-Bridging Cultures, Languages, and Domains in Video Comprehension
Assessing the video comprehension capabilities of multimodal AI systems can effectively measure their understanding and reasoning abilities.
A Unified Agentic Framework for Evaluating Conditional Image Generation
This paper introduces CIGEval, a unified agentic framework for comprehensive evaluation of conditional image generation tasks.
DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation
Despite the increased discourse challenges introduced by noise from automatic speech recognition (ASR), the integration of document-level context in speech translation (ST) remains insufficiently explored.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+8
Short Video Segment-level User Dynamic Interests Modeling in Personalized Recommendation
In contrast, our research focuses on segment-level user interest modeling, which is crucial for understanding how users' preferences evolve during video browsing.
Collaborative LLM Numerical Reasoning with Local Data Protection
Furthermore, our method improves accuracy by 16. 2% - 43. 6% while reducing data leakage by 2. 3% - 44. 6% compared to existing data protection approaches.
Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains
Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs), especially when structured reference answers are accessible for verification.
Graph-Structured Driven Dual Adaptation for Mitigating Popularity Bias
Existing supervised alignment and reweighting methods mitigate this bias but have key limitations: (1) ignoring inherent variability across Graph Convolutional Networks (GCNs) layers, causing negative effects in deeper layers; (2) reliance on fixed hyperparameters to balance item popularity, restricting adaptability and increasing complexity.
InPO: Inversion Preference Optimization with Reparametrized DDIM for Efficient Diffusion Model Alignment
To address these limitations, we introduce DDIM-InPO, an efficient method for direct preference alignment of diffusion models.
AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration
Multi-agent systems (MAS) based on large language models (LLMs) have demonstrated significant potential in collaborative problem-solving.
MoK-RAG: Mixture of Knowledge Paths Enhanced Retrieval-Augmented Generation for Embodied AI Environments
While human cognition inherently retrieves information from diverse and specialized knowledge sources during decision-making processes, current Retrieval-Augmented Generation (RAG) systems typically operate through single-source knowledge retrieval, leading to a cognitive-algorithmic discrepancy.
Adaptive Inner Speech-Text Alignment for LLM-based Speech Translation
Recent advancement of large language models (LLMs) has led to significant breakthroughs across various tasks, laying the foundation for the development of LLM-based speech translation systems.
Representation-based Reward Modeling for Efficient Safety Alignment of Large Language Model
Reinforcement Learning (RL) algorithms for safety alignment of Large Language Models (LLMs), such as Direct Preference Optimization (DPO), encounter the challenge of distribution shift.
Take Off the Training Wheels Progressive In-Context Learning for Effective Alignment
We find that the transformer embeds the task function learned from demonstrations into the separator token representation, which plays an important role in the generation of prior response tokens.
XIFBench: Evaluating Large Language Models on Multilingual Instruction Following
Large Language Models (LLMs) have demonstrated remarkable instruction-following capabilities across various applications.
IDInit: A Universal and Stable Initialization Method for Neural Network Training
Addressing this concern, we introduce fully identical initialization (IDInit), a novel method that preserves identity in both the main and sub-stem layers of residual networks.
Generator-Assistant Stepwise Rollback Framework for Large Language Model Agent
Large language model (LLM) agents typically adopt a step-by-step reasoning framework, in which they interleave the processes of thinking and acting to accomplish the given task.
The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agents
Large Language Models (LLMs) have made remarkable advances in role-playing dialogue agents, demonstrating their utility in character simulations.
Picking the Cream of the Crop: Visual-Centric Data Selection with Collaborative Agents
Specifically, our approach consists of 1) an image information quantification method via visual agents collaboration to select images with rich visual information, and 2) a visual-centric instruction quality assessment method to select high-quality instruction data related to high-quality images.
Evaluating Intelligence via Trial and Error
When the expectation and variance of failure counts are both finite, it signals the ability to consistently find solutions to new challenges, which we define as the Autonomous Level of intelligence.
A 106K Multi-Topic Multilingual Conversational User Dataset with Emoticons
Our in-depth experiments, both quantitative and qualitative, demonstrate the dataset's potential in modeling user behavior and personalized recommendation systems, opening up new possibilities for research in personalized retrieval and conversational AI.
LevelRAG: Enhancing Retrieval-Augmented Generation with Multi-hop Logic Planning over Rewriting Augmented Searchers
In LevelRAG, the high-level searcher orchestrates the retrieval logic, while the low-level searchers (sparse, web, and dense) refine the queries for optimal retrieval.
ASurvey: Spatiotemporal Consistency in Video Generation
Video generation, by leveraging a dynamic visual generation method, pushes the boundaries of Artificial Intelligence Generated Content (AIGC).
A Training-free LLM-based Approach to General Chinese Character Error Correction
To address this issue, we introduce the task of General Chinese Character Error Correction (C2EC), which focuses on all three types of character errors.
Improving Value-based Process Verifier via Structural Prior Injection
In the Large Language Model(LLM) reasoning scenario, people often estimate state value via Monte Carlo sampling.
Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders
Connecting audio encoders with large language models (LLMs) allows the LLM to perform various audio understanding tasks, such as automatic speech recognition (ASR) and audio captioning (AC).
Revealing and Mitigating Over-Attention in Knowledge Editing
Large Language Models have demonstrated superior performance across a wide range of tasks, but they still exhibit undesirable errors due to incorrect knowledge learned from the training data.
PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models
To explore the real limit of PTQ, we propose an extremely low-bit PTQ method called PTQ1. 61, which enables weight quantization to 1. 61-bit for the first time.
Towards Text-Image Interleaved Retrieval
In this work, we introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences, and the model is required to understand the semantics from the interleaved context for effective retrieval.
Benchmarking Post-Training Quantization in LLMs: Comprehensive Taxonomy, Unified Evaluation, and Comparative Analysis
Then, we conduct extensive experiments with the baseline within each class, covering models with various sizes (7B-70B), bitwidths, training levels (LLaMA1/2/3/3. 1), architectures (Mixtral, DeepSeekMoE and Mamba) and modality (LLaVA1. 5 and VILA1. 5) on a wide range of evaluation metrics. Through comparative analysis on the results, we summarize the superior of each PTQ strategy and modelsize-bitwidth trade-off considering the performance.
Exploring Translation Mechanism of Large Language Models
Large language models (LLMs) have succeeded remarkably in multilingual translation tasks.
Evaluating o1-Like LLMs: Unlocking Reasoning for Translation through Comprehensive Analysis
The o1-Like LLMs are transforming AI by simulating human cognitive processes, but their performance in multilingual machine translation (MMT) remains underexplored.
SSVEP-BiMA: Bifocal Masking Attention Leveraging Native and Symmetric-Antisymmetric Components for Robust SSVEP Decoding
Brain-computer interface (BCI) based on steady-state visual evoked potentials (SSVEP) is a popular paradigm for its simplicity and high information transfer rate (ITR).
Labeling Synthetic Content: User Perceptions of Warning Label Designs for AI-generated Content on Social Media
However their trust in the label significantly varied based on the label design.
Semantic Role Labeling: A Systematical Survey
Semantic role labeling (SRL) is a central natural language processing (NLP) task aiming to understand the semantic roles within texts, facilitating a wide range of downstream applications.
FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces
Virtual film production requires intricate decision-making processes, including scriptwriting, virtual cinematography, and precise actor positioning and actions.
Optimizing Speech Multi-View Feature Fusion through Conditional Computation
Recent advancements have highlighted the efficacy of self-supervised learning (SSL) features in various speech-related tasks, providing lightweight and versatile multi-view speech representations.
EEG-ReMinD: Enhancing Neurodegenerative EEG Decoding through Self-Supervised State Reconstruction-Primed Riemannian Dynamics
The development of EEG decoding algorithms confronts challenges such as data sparsity, subject variability, and the need for precise annotations, all of which are vital for advancing brain-computer interfaces and enhancing the diagnosis of diseases.
Continuous Knowledge-Preserving Decomposition for Few-Shot Continual Learning
To this end, we propose Continuous Knowledge-Preserving Decomposition for FSCIL (CKPD-FSCIL), a framework that decomposes a model's weights into two parts: one that compacts existing knowledge (knowledge-sensitive components) and another that carries redundant capacity to accommodate new abilities (redundant-capacity components).
class-incremental learning
Few-Shot Class-Incremental Learning
+1
Investigating Numerical Translation with Large Language Models
The inaccurate translation of numbers can lead to significant security issues, ranging from financial setbacks to medical inaccuracies.
Improving GenIR Systems Based on User Feedback
In this chapter, we discuss how to improve the GenIR systems based on user feedback.
Test-time Computing: from System-1 Thinking to System-2 Thinking
In System-2 models, it enhances the model's reasoning ability to solve complex problems through repeated sampling, self-correction, and tree search.
KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
As retrieval-augmented generation prevails in large language models, embedding models are becoming increasingly crucial.
Bridging Modalities: Improving Universal Multimodal Retrieval by Multimodal Large Language Models
Last, we provide in-depth analyses of model scaling and training strategies, and perform ablation studies on both the model and synthetic data.
Dialogue Director: Bridging the Gap in Dialogue Visualization for Multimodal Storytelling
Recent advances in AI-driven storytelling have enhanced video generation and story visualization.
MAFT: Efficient Model-Agnostic Fairness Testing for Deep Neural Networks via Zero-Order Gradient Search
Some efficient white-box fairness testing methods about individual fairness have been proposed.
"I've Heard of You!": Generate Spoken Named Entity Recognition Data for Unseen Entities
Spoken named entity recognition (NER) aims to identify named entities from speech, playing an important role in speech processing.
RaSeRec: Retrieval-Augmented Sequential Recommendation
Although prevailing supervised and self-supervised learning (SSL)-augmented sequential recommendation (SeRec) models have achieved improved performance with powerful neural network architectures, we argue that they still suffer from two limitations: (1) Preference Drift, where models trained on past data can hardly accommodate evolving user preference; and (2) Implicit Memory, where head patterns dominate parametric learning, making it harder to recall long tails.
Ranked #2 on
Sequential Recommendation
on Amazon-Beauty
GME: Improving Universal Multimodal Retrieval by Multimodal LLMs
Last, we provide in-depth analyses of model scaling and training strategies, and perform ablation studies on both the model and synthetic data.
DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs
Efficient KV cache management in LLMs is crucial for long-context tasks like RAG and summarization.
Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering
Multi-hop question answering (MHQA) poses a significant challenge for large language models (LLMs) due to the extensive knowledge demands involved.
Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning
To study the reason behind these limitations, we propose VGCure, a comprehensive benchmark covering 22 tasks for examining the fundamental graph understanding and reasoning capacities of LVLMs.
Efficient Speech Command Recognition Leveraging Spiking Neural Network and Curriculum Learning-based Knowledge Distillation
Furthermore, by executing KDCL, we reduce the number of time steps by 60% and decrease energy consumption by 54. 8% while maintaining comparable performance to recent SOTA results.
DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling Check
One key characteristic of the Chinese spelling check (CSC) task is that incorrect characters are usually similar to the correct ones in either phonetics or glyph.
LinguaLIFT: An Effective Two-stage Instruction Tuning Framework for Low-Resource Language Tasks
Large language models (LLMs) have demonstrated impressive multilingual understanding and reasoning capabilities, driven by extensive pre-training multilingual corpora and fine-tuning instruction data.
Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine Translation
Visual information has been introduced for enhancing machine translation (MT), and its effectiveness heavily relies on the availability of large amounts of bilingual parallel sentence pairs with manual image annotations.
LLM-based Discriminative Reasoning for Knowledge Graph Question Answering
Large language models (LLMs) based on generative pre-trained Transformer have achieved remarkable performance on knowledge graph question-answering (KGQA) tasks.
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions
Recent advancements in multimodal large language models (MLLMs) have made significant strides in open-world understanding.
ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty
To accelerate the inference of LLMs, storing computed caches in memory has become the standard technique.
Look Before You Leap: Enhancing Attention and Vigilance Regarding Harmful Content with GuidelineLLM
This vulnerability poses significant risks to the real-world applications.
CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models
Large Language Models (LLMs) need to adapt to the continuous changes in data, tasks, and user preferences.
Multi-Level Correlation Network For Few-Shot Image Classification
In this paper, we argue that measure at such a level may not be effective enough to generalize from base to novel classes when using only a few images.
Towards Rich Emotions in 3D Avatars: A Text-to-3D Avatar Generation Benchmark
T3DEM is the most crucial step in determining the quality of Emo3D generation and encompasses three key challenges: Expression Diversity, Emotion-Content Consistency, and Expression Fluidity.
Learning Monotonic Attention in Transducer for Streaming Generation
Streaming generation models are increasingly utilized across various fields, with the Transducer architecture being particularly popular in industrial applications.
DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization
To address this, we propose DRPruning, which incorporates distributionally robust optimization to restore balanced performance across domains, along with further improvements to enhance robustness.
Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM
Existing research primarily utilizes additional text data and predefined speech styles supported by TTS models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Interpret the Internal States of Recommendation Model with Sparse Autoencoder
Firstly, we train an autoencoder with sparsity constraints to reconstruct internal activations of recommendation models, making the RecSAE latents more interpretable and monosemantic than the original neuron activations.
Beyond Utility: Evaluating LLM as Recommender
We intend our evaluation framework and observations to benefit future research on the use of LLMs as recommenders.
PerSRV: Personalized Sticker Retrieval with Vision-Language Model
The online retrieval part follows the paradigm of relevant recall and personalized ranking, supported by the offline pre-calculation parts, which are sticker semantic understanding, utility evaluation and personalization modules.
NewTerm: Benchmarking Real-Time New Terms for Large Language Models with Annual Updates
Despite their remarkable abilities in various tasks, large language models (LLMs) still struggle with real-time information (e. g., new facts and terms) due to the knowledge cutoff in their development process.
LOGO -- Long cOntext aliGnment via efficient preference Optimization
To overcome the GPU memory-bound issue caused by the long sequence, LOGO employs a reference-free preference optimization strategy and adopts a position synthesis method to construct the training data.
Unleashing Reasoning Capability of LLMs via Scalable Question Synthesis from Scratch
The availability of high-quality data is one of the most important factors in improving the reasoning capability of LLMs.
Beware of Calibration Data for Pruning Large Language Models
As large language models (LLMs) are widely applied across various fields, model compression has become increasingly crucial for reducing costs and improving inference efficiency.
Revealing and Mitigating the Local Pattern Shortcuts of Mamba
Large language models (LLMs) have advanced significantly due to the attention mechanism, but their quadratic complexity and linear memory demands limit their performance on long-context tasks.
Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image
In the visual spatial understanding (VSU) area, spatial image-to-text (SI2T) and spatial text-to-image (ST2I) are two fundamental tasks that appear in dual form.
BrainECHO: Semantic Brain Signal Decoding through Vector-Quantized Spectrogram Reconstruction for Whisper-Enhanced Text Generation
Current EEG/MEG-to-text decoding systems suffer from three key limitations: (1) reliance on teacher-forcing methods, which compromises robustness during inference, (2) sensitivity to session-specific noise, hindering generalization across subjects, and (3) misalignment between brain signals and linguistic representations due to pre-trained language model over-dominance.
MoDification: Mixture of Depths Made Easy
Long-context efficiency has recently become a trending topic in serving large language models (LLMs).
LLM-based Translation Inference with Iterative Bilingual Understanding
The remarkable understanding and generation capabilities of large language models (LLMs) have greatly improved translation performance.
An Automatic and Cost-Efficient Peer-Review Framework for Language Generation Evaluation
Moreover, our study highlights the impact of prompt strategies and evaluation formats on evaluation performance, offering guidance for method optimization in the future.
SEER: Self-Aligned Evidence Extraction for Retrieval-Augmented Generation
Recent studies in Retrieval-Augmented Generation (RAG) have investigated extracting evidence from retrieved passages to reduce computational costs and enhance the final RAG performance, yet it remains challenging.
Medico: Towards Hallucination Detection and Correction with Multi-source Evidence Fusion
Therefore, it is necessary to resort to external knowledge to detect and correct the hallucinated content.
DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory
Large language models (LLMs) have achieved reasonable quality improvements in machine translation (MT).
StepTool: A Step-grained Reinforcement Learning Framework for Tool Learning in LLMs
Despite having powerful reasoning and inference capabilities, Large Language Models (LLMs) still need external tools to acquire real-time information retrieval or domain-specific expertise to solve complex tasks, which is referred to as tool learning.
Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large Language Models
The scaling of large language models (LLMs) is a critical research area for the efficiency and effectiveness of model training and deployment.
A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction Based on Large Language Models
This work proposes a simple training-free prompt-free approach to leverage large language models (LLMs) for the Chinese spelling correction (CSC) task, which is totally different from all previous CSC approaches.
Self-Powered LLM Modality Expansion for Large Speech-Text Models
This study aims to refine the use of speech datasets for LSM training by addressing the limitations of vanilla instruction tuning.
CommonIT: Commonality-Aware Instruction Tuning for Large Language Models via Data Partitions
With instruction tuning, Large Language Models (LLMs) can enhance their ability to adhere to commands.
Parameter Competition Balancing for Model Merging
Recently developed model merging techniques enable the direct integration of multiple models, each fine-tuned for distinct tasks, into a single model.
L-CiteEval: Do Long-Context Models Truly Leverage Context for Responding?
Long-context models (LCMs) have made remarkable strides in recent years, offering users great convenience for handling tasks that involve long context, such as document summarization.
Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answering
Knowledge graph question answering (KGQA) involves answering natural language questions by leveraging structured information stored in a knowledge graph.
Dynamic Planning for LLM-based Graphical User Interface Automation
However, a key challenge lies in devising effective plans to guide action prediction in GUI tasks, though planning have been widely recognized as effective for decomposing complex tasks into a series of steps.
Grammar Induction from Visual, Speech and Text
Grammar Induction could benefit from rich heterogeneous signals, such as text, vision, and acoustics.
ProFD: Prompt-Guided Feature Disentangling for Occluded Person Re-Identification
To address the occlusion issues in person Re-Identification (ReID) tasks, many methods have been proposed to extract part features by introducing external spatial information.
Large Language Model Should Understand Pinyin for Chinese ASR Error Correction
Large language models can enhance automatic speech recognition systems through generative error correction.
Exploring and Enhancing the Transfer of Distribution in Knowledge Distillation for Autoregressive Language Models
Knowledge distillation (KD) is a technique that compresses large teacher models by training smaller student models to mimic them.
LA-RAG:Enhancing LLM-based ASR Accuracy with Retrieval-Augmented Generation
Recent advancements in integrating speech information into large language models (LLMs) have significantly improved automatic speech recognition (ASR) accuracy.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
PiTe: Pixel-Temporal Alignment for Large Video-Language Model
Fueled by the Large Language Models (LLMs) wave, Large Visual-Language Models (LVLMs) have emerged as a pivotal advancement, bridging the gap between image and text.
Semantic-Guided Multimodal Sentiment Decoding with Adversarial Temporal-Invariant Learning
Multimodal sentiment analysis aims to learn representations from different modalities to identify human emotions.
MemLong: Memory-Augmented Retrieval for Long Text Modeling
This work introduces MemLong: Memory-Augmented Retrieval for Long Text Generation, a method designed to enhance the capabilities of long-context language modeling by utilizing an external retriever for historical information retrieval.
Focus-Consistent Multi-Level Aggregation for Compositional Zero-Shot Learning
To transfer knowledge from seen attribute-object compositions to recognize unseen ones, recent compositional zero-shot learning (CZSL) methods mainly discuss the optimal classification branches to identify the elements, leading to the popularity of employing a three-branch architecture.
TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models
In this paper, we analyze the core mechanisms of previous predominant adversarial attack methods, revealing that 1) the distributions of importance score differ markedly among victim models, restricting the transferability; 2) the sequential attack processes induces substantial time overheads.
LLM with Relation Classifier for Document-Level Relation Extraction
Large language models (LLMs) have created a new paradigm for natural language processing.
ConflictBank: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLM
Only a few research explored the conflicts between the inherent knowledge of LLMs and the retrieved contextual knowledge.
Large Language Models for Classical Chinese Poetry Translation: Benchmarking, Evaluating, and Improving
Different from the traditional translation tasks, classical Chinese poetry translation requires both adequacy and fluency in translating culturally and historically significant content and linguistic poetic elegance.
Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation
These images are designed to maintain visual consistency across different scenes using a visual-language prompting method that combines scene descriptions and images of the appearing character and setting.
An End-to-End Model for Photo-Sharing Multi-modal Dialogue Generation
We propose the first end-to-end model for photo-sharing multi-modal dialogue generation, which integrates an image perceptron and an image generator with a large language model.
Model Hijacking Attack in Federated Learning
Machine learning (ML), driven by prominent paradigms such as centralized and federated learning, has made significant progress in various critical applications ranging from autonomous driving to face recognition.
mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval
We first introduce a text encoder (base size) enhanced with RoPE and unpadding, pre-trained in a native 8192-token context (longer than 512 of previous multilingual encoders).
SeqMIA: Sequential-Metric Based Membership Inference Attack
Building upon this signal, we introduce a novel attack method called Sequential-metric based Membership Inference Attack (SeqMIA).
LeKUBE: A Legal Knowledge Update BEnchmark
Existing benchmarks for evaluating knowledge update methods are mostly designed for the open domain and cannot address the specific challenges of the legal domain, such as the nuanced application of new legal knowledge, the complexity and lengthiness of legal regulations, and the intricate nature of legal reasoning.
Mamba-FSCIL: Dynamic Adaptation with Selective State Space Model for Few-Shot Class-Incremental Learning
The dual design enables the model to maintain the robust features of base classes, while adaptively learning distinctive feature shifts for novel classes.
class-incremental learning
Few-Shot Class-Incremental Learning
+3
MFE-ETP: A Comprehensive Evaluation Benchmark for Multi-modal Foundation Models on Embodied Task Planning
To this end, based on the characteristics of embodied task planning, we first develop a systematic evaluation framework, which encapsulates four crucial capabilities of MFMs: object understanding, spatio-temporal perception, task understanding, and embodied reasoning.
Translatotron-V(ison): An End-to-End Model for In-Image Machine Translation
Among them, the target text decoder is used to alleviate the language alignment burden, and the image tokenizer converts long sequences of pixels into shorter sequences of visual tokens, preventing the model from focusing on low-level visual features.
AMA-LSTM: Pioneering Robust and Fair Financial Audio Analysis for Stock Volatility Prediction
This confirms the value of adversarial training in reducing stochasticity and bias for stock volatility prediction tasks.
Feature-Specific Coefficients of Determination in Tree Ensembles
Tree ensemble methods provide promising predictions with models difficult to interpret.
Concise and Precise Context Compression for Tool-Using Language Models
However, when compressing tool documentation, existing methods suffer from the weaknesses of key information loss (specifically, tool/parameter name errors) and difficulty in adjusting the length of compressed sequences based on documentation lengths.
Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment
Then, an SG-based framework is built, where the textual SG (TSG) is encoded with a graph Transformer, while the video dynamic SG (DSG) and the HSG are modeled with a novel recurrent graph Transformer for spatial and temporal feature propagation.
LLM-Driven Multimodal Opinion Expression Identification
We introduce a novel multimodal OEI (MOEI) task, integrating text and speech to mirror real-world scenarios.
OPT-Tree: Speculative Decoding with Adaptive Draft Tree Structure
It searches the optimal tree structure that maximizes the mathematical expectation of the acceptance length in each decoding step.
Retrieval-style In-Context Learning for Few-shot Hierarchical Text Classification
Hierarchical text classification (HTC) is an important task with broad applications, while few-shot HTC has gained increasing interest recently.
Timo: Towards Better Temporal Reasoning for Language Models
Therefore, we propose a crucial question: Can we build a universal framework to handle a variety of temporal reasoning tasks?
Understanding the RoPE Extensions of Long-Context LLMs: An Attention Perspective
Enabling LLMs to handle lengthy context is currently a research hotspot.
A Survey on Human Preference Learning for Large Language Models
In this survey, we review the progress in exploring human preference learning for LLMs from a preference-centered perspective, covering the sources and formats of preference feedback, the modeling and usage of preference signals, as well as the evaluation of the aligned LLMs.
VideoVista: A Versatile Benchmark for Video Understanding and Reasoning
Through a comprehensive and quantitative evaluation of cutting-edge models, we reveal that: 1) Video-LMMs face difficulties in fine-grained video tasks involving temporal location, object tracking, and anomaly detection; 2) Video-LMMs present inferior logical and relation reasoning abilities; 3) Open-source Video-LMMs' performance is significantly lower than GPT-4o and Gemini-1. 5, lagging by 20 points.
LAIP: Learning Local Alignment from Image-Phrase Modeling for Text-based Person Search
This paper proposes the Local Alignment from Image-Phrase modeling (LAIP) framework, with Bidirectional Attention-weighted local alignment (BidirAtt) and Mask Phrase Modeling (MPM) module. BidirAtt goes beyond the typical forward attention by considering the gradient of the transformer as backward attention, utilizing two-sided information for local alignment.
Living in the Moment: Can Large Language Models Grasp Co-Temporal Reasoning?
Temporal reasoning is fundamental for large language models (LLMs) to comprehend the world.
TasTe: Teaching Large Language Models to Translate through Self-Reflection
The evaluation results in four language directions on the WMT22 benchmark reveal the effectiveness of our approach compared to existing methods.
Agent-SiMT: Agent-assisted Simultaneous Machine Translation with Large Language Models
Simultaneous Machine Translation (SiMT) generates target translations while reading the source sentence.
On the Hallucination in Simultaneous Machine Translation
It is widely known that hallucination is a critical issue in Simultaneous Machine Translation (SiMT) due to the absence of source-side information.
DUAL-REFLECT: Enhancing Large Language Models for Reflective Translation through Dual Learning Feedback Mechanisms
Recently, large language models (LLMs) enhanced by self-reflection have achieved promising performance on machine translation.
A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation
Simultaneous translation models play a crucial role in facilitating communication.
Paying More Attention to Source Context: Mitigating Unfaithful Translations from Large Language Model
Large language models (LLMs) have showcased impressive multilingual machine translation ability.
CTC-based Non-autoregressive Textless Speech-to-Speech Translation
Direct speech-to-speech translation (S2ST) has achieved impressive translation quality, but it often faces the challenge of slow decoding due to the considerable length of speech sequences.
Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?
Recently proposed two-pass direct speech-to-speech translation (S2ST) models decompose the task into speech-to-text translation (S2TT) and text-to-speech (TTS) within an end-to-end model, yielding promising results.
Efficient k-Nearest-Neighbor Machine Translation with Dynamic Retrieval
In this paper, we first conduct a preliminary study to reveal two key limitations of $k$NN-MT-AR: 1) the optimization gap leads to inaccurate estimation of $\lambda$ for determining $k$NN retrieval skipping, and 2) using a fixed threshold fails to accommodate the dynamic demands for $k$NN retrieval at different timesteps.
AutoSurvey: Large Language Models Can Automatically Write Surveys
This paper introduces AutoSurvey, a speedy and well-organized methodology for automating the creation of comprehensive literature surveys in rapidly evolving fields like artificial intelligence.
StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning
Simultaneous speech-to-speech translation (Simul-S2ST, a. k. a streaming speech translation) outputs target speech while receiving streaming speech inputs, which is critical for real-time communication.
Ranked #1 on
de-en
on CVSS
Large Language Models as Evaluators for Recommendation Explanations
We also provide further insights into combining human labels with the LLM evaluation process and utilizing ensembles of multiple heterogeneous LLM evaluators to enhance the accuracy and stability of evaluations.
Multimodal Reasoning with Multimodal Knowledge Graph
Multimodal reasoning with large language models (LLMs) often suffers from hallucinations and the presence of deficient or outdated knowledge within LLMs.
Demonstration Augmentation for Zero-shot In-context Learning
Large Language Models (LLMs) have demonstrated an impressive capability known as In-context Learning (ICL), which enables them to acquire knowledge from textual demonstrations without the need for parameter updates.
Popularity-Aware Alignment and Contrast for Mitigating Popularity Bias
To alleviate popularity bias, existing efforts focus on emphasizing unpopular items or separating the correlation between item representations and their popularity.
ReChorus2.0: A Modular and Task-Flexible Recommendation Library
However, these libraries often impose certain restrictions on data and seldom support the same model to perform different tasks and input formats, limiting users from customized explorations.
From Role-Play to Drama-Interaction: An LLM Solution
Drama is a form of storytelling inspired by human creativity, proceeding with a predefined storyline, carrying emotions and thoughts.
Why Not Transform Chat Large Language Models to Non-English?
For the second issue, we propose a method comprising two synergistic components: low-rank adaptation for training to maintain the original LLM parameters, and recovery KD, which utilizes data generated by the chat LLM itself to recover the original knowledge from the frozen parameters.
