Search Results for author:
Found 331 papers, 134 papers with code
Maximal Clique Based Non-Autoregressive Open Information Extraction
However, the popular OpenIE systems usually output facts sequentially in the way of predicting the next fact conditioned on the previous decoded ones, which enforce an unnecessary order on the facts and involve the error accumulation between autoregressive steps.
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.
C^3KG: A Chinese Commonsense Conversation Knowledge Graph
Existing commonsense knowledge bases often organize tuples in an isolated manner, which is deficient for commonsense conversational models to plan the next steps.
BIT-Xiaomi’s System for AutoSimTrans 2022
This system paper describes the BIT-Xiaomi simultaneous translation system for Autosimtrans 2022 simultaneous translation challenge.
A Novel Line Integral Transform for 2D Affine-Invariant Shape Retrieval
While conducting the trace transform once only generates a single feature and multiple trace transforms of different functionals are needed to derive more to make the descriptors informative.
The Xiaomi Text-to-Text Simultaneous Speech Translation System for IWSLT 2022
Our system is built based on the Transformer model with novel techniques borrowed from our recent research work.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation
In this paper, we introduce OHRBench, the first benchmark for understanding the cascading impact of OCR on RAG systems.
Optical Character Recognition
Optical Character Recognition (OCR)
+2
Seq2Time: Sequential Knowledge Transfer for Video LLM Temporal Grounding
Temporal awareness is essential for video large language models (LLMs) to understand and reason about events within long videos, enabling applications like dense video captioning and temporal video grounding in a unified system.
HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and Extrapolation
Furthermore, we conduct a detailed analysis of rotary position encoding (RoPE, a prevalent relative positional encoding in LLMs), and found that the U-shape attention is caused by some learned components, which are also the key factor limiting RoPE's expressiveness and extrapolation. Inspired by these insights, we propose High-frequency rotary Position Encoding (HoPE).
Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction
Document parsing is essential for converting unstructured and semi-structured documents-such as contracts, academic papers, and invoices-into structured, machine-readable data.
DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization
Finally, our method can identify an optimal SubNet through few-step gradient optimization and a simple post-processing procedure.
SiamSeg: Self-Training with Contrastive Learning for Unsupervised Domain Adaptation Semantic Segmentation in Remote Sensing
However, the application of ST to RS image segmentation remains underexplored.
DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception
Pre-training on the resulting DocSynth-300K dataset significantly improves fine-tuning performance across various document types.
Order-aware Interactive Segmentation
However, current methods often fail to accurately separate target objects from the background, due to a limited understanding of order, the relative depth between objects in a scene.
3-D Magnetotelluric Deep Learning Inversion Guided by Pseudo-Physical Information
To efficiently achieve data-physical dual-driven MT deep learning inversion for large-scale 3-D MT data, we propose using DL forward modeling networks to compute this portion of the loss.
CALoR: Towards Comprehensive Model Inversion Defense
Model Inversion Attacks (MIAs) aim at recovering privacy-sensitive training data from the knowledge encoded in the released machine learning models.
MinerU: An Open-Source Solution for Precise Document Content Extraction
Document content analysis has been a crucial research area in computer vision.
PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning
Low-rank adaptation (LoRA) and its variants have recently gained much interest due to their ability to avoid excessive inference costs.
MobileVLM: A Vision-Language Model for Better Intra- and Inter-UI Understanding
These fine-tuned VLMs may still ignore the relationships between UI pages, neglect the roles of elements in page transitions and lack inter-UI understanding.
ToolPlanner: A Tool Augmented LLM for Multi Granularity Instructions with Path Planning and Feedback
Recently, tool-augmented LLMs have gained increasing attention.
Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data
Despite recent advances in training and prompting strategies for Large Language Models (LLMs), these models continue to face challenges with complex logical reasoning tasks that involve long reasoning chains.
An Enhanced-State Reinforcement Learning Algorithm for Multi-Task Fusion in Large-Scale Recommender Systems
However, limited by their modeling pattern, all the current RL-MTF methods can only utilize user features as the state to generate actions for each user, but unable to make use of item features and other valuable features, which leads to suboptimal results.
Mixture of Diverse Size Experts
The Sparsely-Activated Mixture-of-Experts (MoE) has gained increasing popularity for scaling up large language models (LLMs) without exploding computational costs.
MoWE-Audio: Multitask AudioLLMs with Mixture of Weak Encoders
The rapid advancements in large language models (LLMs) have significantly enhanced natural language processing capabilities, facilitating the development of AudioLLMs that process and understand speech and audio inputs alongside text.
UMOD: A Novel and Effective Urban Metro Origin-Destination Flow Prediction Method
Accurate prediction of metro Origin-Destination (OD) flow is essential for the development of intelligent transportation systems and effective urban traffic management.
CDM: A Reliable Metric for Fair and Accurate Formula Recognition Evaluation
Such a spatially-aware and character-matching method offers a more accurate and equitable evaluation compared with previous BLEU and Edit Distance metrics that rely solely on text-based character matching.
ToolACE: Winning the Points of LLM Function Calling
Function calling significantly extends the application boundary of large language models, where high-quality and diverse training data is critical for unlocking this capability.
PuYun: Medium-Range Global Weather Forecasting Using Large Kernel Attention Convolutional Networks
This approach enhances the accuracy of 10-day weather forecasting.
Segmentation-guided Layer-wise Image Vectorization with Gradient Fills
The widespread use of vector graphics creates a significant demand for vectorization methods.
IAA: Inner-Adaptor Architecture Empowers Frozen Large Language Model with Multimodal Capabilities
Building on the strategy of freezing the language model, we conduct thorough structural exploration and introduce the Inner-Adaptor Architecture (IAA).
Understanding Literary Texts by LLMs: A Case Study of Ancient Chinese Poetry
Additionally, evaluating literary works is often complex and hard to fully quantify, which directly hinders the further development of AI creation.
TDS-CLIP: Temporal Difference Side Network for Image-to-Video Transfer Learning
Therefore, in this paper, we propose a memory-efficient Temporal Difference Side Network (TDS-CLIP) to balance knowledge transferring and temporal modeling, avoiding backpropagation in frozen parameter models.
Ranked #6 on
Action Recognition
on Something-Something V1
CSI-Free Position Optimization for Movable Antenna Communication Systems: A Black-Box Optimization Approach
Movable antenna (MA) is a new technology which leverages local movement of antennas to improve channel qualities and enhance the communication performance.
In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models
By applying our algorithm to instruction fine-tuning data of LLMs, we can achieve similar performance with just 50% of the training data.
Walk Wisely on Graph: Knowledge Graph Reasoning with Dual Agents via Efficient Guidance-Exploration
The high-level agent walks on the simplified knowledge graph to provide stage-wise hints for the low-level agent walking on the original knowledge graph.
Image Re-Identification: Where Self-supervision Meets Vision-Language Learning
Recently, large-scale vision-language pre-trained models like CLIP have shown impressive performance in image re-identification (ReID).
A New Dataset and Framework for Real-World Blurred Images Super-Resolution
However, we find that the efficacy of recent methods obviously diminishes when employed on image data with blur, while image data with intentional blur constitute a substantial proportion of general data.
Learning Structurally Stabilized Representations for Multi-modal Lossless DNA Storage
By incorporating these novel strategies, the proposed RSRL can learn highly durable, dense, and lossless representations for the subsequent storage tasks into DNA sequences.
Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations
However, as the coarse-grained structured pruning poses large damage to the highly interconnected model, achieving a high compression ratio for scaled-up LLMs remains a challenge.
InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output
This long-context capability allows IXC-2. 5 to excel in tasks requiring extensive input and output contexts.
Ranked #12 on
Temporal Relation Extraction
on Vinoground
Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents
With the remarkable advancements of large language models (LLMs), LLM-based agents have become a research hotspot in human-computer interaction.
A Cross Spatio-Temporal Pathology-based Lung Nodule Dataset
Recently, intelligent analysis of lung nodules with the assistant of computer aided detection (CAD) techniques can improve the accuracy rate of lung cancer diagnosis.
AudioBench: A Universal Benchmark for Audio Large Language Models
We introduce AudioBench, a universal benchmark designed to evaluate Audio Large Language Models (AudioLLMs).
Ranked #1 on
Audio Scene Understanding
on Clotho-AQA
Gaze-directed Vision GNN for Mitigating Shortcut Learning in Medical Image
In this paper, we propose a novel gaze-directed Vision GNN (called GD-ViG) to leverage the visual patterns of radiologists from gaze as expert knowledge, directing the network toward disease-relevant regions, and thereby mitigating shortcut learning.
Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding
Automated audio captioning (AAC) is an audio-to-text task to describe audio contents in natural language.
Ranked #2 on
Audio captioning
on Clotho
(using extra training data)
DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models
Scientific documents record research findings and valuable human knowledge, comprising a vast corpus of high-quality data.
SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages
Southeast Asia (SEA) is a region rich in linguistic diversity and cultural variety, with over 1, 300 indigenous languages and a population of 671 million people.
OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text
In this paper, we introduce OmniCorpus, a 10 billion-scale image-text interleaved dataset.
Bridging Language Gaps in Audio-Text Retrieval
The predominant focus of existing research on English descriptions poses a limitation on the applicability of such models, given the abundance of non-English content in real-world data.
OpenDataLab: Empowering General Artificial Intelligence with Open Datasets
The dispersion of data sources and diversity of data formats often lead to inefficiencies in data retrieval and processing, significantly impeding the progress of AI research and applications.
SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM
In inference, it boosts speeds by up to 37% and reduces memory by 1GB per GPU.
DSDL: Data Set Description Language for Bridging Modalities and Tasks in AI Data
In the era of artificial intelligence, the diversity of data modalities and annotation formats often renders data unusable directly, requiring understanding and format conversion before it can be used by researchers or developers with different needs.
CapS-Adapter: Caption-based MultiModal Adapter in Zero-Shot Classification
Our method achieves outstanding zero-shot classification results across 19 benchmark datasets, improving accuracy by 2. 19\% over the previous leading method.
Enhancing User Interest based on Stream Clustering and Memory Networks in Large-Scale Recommender Systems
Recommender Systems (RSs) provide personalized recommendation service based on user interest, which are widely used in various platforms.
Large-Scale Multi-Center CT and MRI Segmentation of Pancreas with Deep Learning
We also collected CT scans of 1, 350 patients from publicly available sources for benchmarking purposes.
MDNet: Multi-Decoder Network for Abdominal CT Organs Segmentation
Each decoder network is connected to a different part of the encoder via a multi-scale feature enhancement dilated block.
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
MLA guarantees efficient inference through significantly compressing the Key-Value (KV) cache into a latent vector, while DeepSeekMoE enables training strong models at an economical cost through sparse computation.
CRAFT: Extracting and Tuning Cultural Instructions from the Wild
Large language models (LLMs) have rapidly evolved as the foundation of various natural language processing (NLP) applications.
PhyRecon: Physically Plausible Neural Scene Reconstruction
In this paper, we introduce PHYRECON, the first approach to leverage both differentiable rendering and differentiable physics simulation to learn implicit surface representations.
How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites
Compared to both open-source and proprietary models, InternVL 1. 5 shows competitive performance, achieving state-of-the-art results in 8 of 18 benchmarks.
Ranked #11 on
Visual Question Answering
on MM-Vet v2
An Off-Policy Reinforcement Learning Algorithm Customized for Multi-Task Fusion in Large-Scale Recommender Systems
Recently, to optimize long-term user satisfaction within a recommendation session, Reinforcement Learning (RL) is used for MTF in the industry.
CrossIn: An Efficient Instruction Tuning Approach for Cross-Lingual Knowledge Alignment
This performance discrepancy mainly stems from the imbalanced distribution of training data across languages during pre-training and instruction tuning stages.
WiTUnet: A U-Shaped Architecture Integrating CNN and Transformer for Improved Feature Alignment and Local Information Fusion
Low-dose computed tomography (LDCT) has become the technology of choice for diagnostic medical imaging, given its lower radiation dose compared to standard CT, despite increasing image noise and potentially affecting diagnostic accuracy.
Resilience of Large Language Models for Noisy Instructions
As the rapidly advancing domain of natural language processing (NLP), large language models (LLMs) have emerged as powerful tools for interpreting human commands and generating text across various tasks.
Automatic Speech Recognition
Optical Character Recognition
+3
InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD
The Large Vision-Language Model (LVLM) field has seen significant advancements, yet its progression has been hindered by challenges in comprehending fine-grained visual content due to limited resolution.
Ranked #32 on
Visual Question Answering
on MM-Vet
InternLM2 Technical Report
The evolution of Large Language Models (LLMs) like ChatGPT and GPT-4 has sparked discussions on the advent of Artificial General Intelligence (AGI).
Ranked #5 on
Long-Context Understanding
on Ada-LEval (BestAnswer)
Distribution-Aware Data Expansion with Diffusion Models
In this paper, we propose DistDiff, a training-free data expansion framework based on the distribution-aware diffusion model.
ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval
Specifically, our proposed ToolRerank includes Adaptive Truncation, which truncates the retrieval results related to seen and unseen tools at different positions, and Hierarchy-Aware Reranking, which makes retrieval results more concentrated for single-tool queries and more diverse for multi-tool queries.
CN-RMA: Combined Network with Ray Marching Aggregation for 3D Indoors Object Detection from Multi-view Images
This paper introduces CN-RMA, a novel approach for 3D indoor object detection from multi-view images.
Communication Efficient ConFederated Learning: An Event-Triggered SAGA Approach
Due to the potentially massive number of users involved, it is crucial to reduce the communication overhead of the CFL system.
A Comprehensive Evaluation of Quantization Strategies for Large Language Models
Our experimental results indicate that LLMs with 4-bit quantization can retain performance comparable to their non-quantized counterparts, and perplexity can serve as a proxy metric for quantized LLMs on most benchmarks.
DRSI-Net: Dual-Residual Spatial Interaction Network for Multi-Person Pose Estimation
To address the above problems, a dual-residual spatial interaction network (DRSI-Net) for MPPE with high accuracy and low complexity is proposed herein.
Active Support of Inverters for Improving Short-Term Voltage Security in 100% IBRsPenetrated Power Systems
Due to the energy crisis and environmental pollution, the installed capacity of inverter-based resources (IBRs) in power grids is rapidly increasing, and grid-following control (GFL) is the most prevalent at present.
In-Context Learning for Few-Shot Nested Named Entity Recognition
In nested Named entity recognition (NER), entities are nested with each other, and thus requiring more data annotations to address.
InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model
We introduce InternLM-XComposer2, a cutting-edge vision-language model excelling in free-form text-image composition and comprehension.
Ranked #15 on
Visual Question Answering
on MM-Vet v2
Impact of Flexible and Bidirectional Charging in Medium- and Heavy-Duty Trucks on California's Decarbonization Pathway
In particular, we examine the potential cost savings of electrical generation infrastructure by enabling flexible charging and bidirectional charging for these trucks.
eCIL-MU: Embedding based Class Incremental Learning and Machine Unlearning
New categories may be introduced over time, or existing categories may need to be reclassified.
Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts
Inspired by the great success of diffusion model in image generation tasks we propose a novel hierarchical framework named as CoTDiffusion that incorporates diffusion model as a high-level planner to convert the general and multi-modal prompts into coherent visual subgoal plans which further guide the low-level policy model before action execution.
CN-RMA: Combined Network with Ray Marching Aggregation for 3D Indoor Object Detection from Multi-view Images
This paper introduces CN-RMA a novel approach for 3D indoor object detection from multi-view images.
Parrot Captions Teach CLIP to Spot Text
Despite CLIP being the foundation model in numerous vision-language applications, the CLIP suffers from a severe text spotting bias.
OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation
Based on the observation, OPERA introduces a penalty term on the model logits during the beam-search decoding to mitigate the over-trust issue, along with a rollback strategy that retrospects the presence of summary tokens in the previously generated tokens, and re-allocate the token selection if necessary.
Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
Multimodal large language models have made significant advancements in recent years, yet they still suffer from a common issue known as the "hallucination problem", in which the models generate textual descriptions that inaccurately depict or entirely fabricate content from associated images.
CBSiMT: Mitigating Hallucination in Simultaneous Machine Translation with Weighted Prefix-to-Prefix Training
Simultaneous machine translation (SiMT) is a challenging task that requires starting translation before the full source sentence is available.
DetermLR: Augmenting LLM-based Logical Reasoning from Indeterminacy to Determinacy
Recent advances in large language models (LLMs) have revolutionized the landscape of reasoning tasks.
Blind Image Super-resolution with Rich Texture-Aware Codebooks
However, we find that a codebook based on HR reconstruction may not effectively capture the complex correlations between low-resolution (LR) and HR images.
F$^2$AT: Feature-Focusing Adversarial Training via Disentanglement of Natural and Perturbed Patterns
We propose a Feature-Focusing Adversarial Training (F$^2$AT), which differs from previous work in that it enforces the model to focus on the core features from natural patterns and reduce the impact of spurious features from perturbed patterns.
EMIT-Diff: Enhancing Medical Image Segmentation via Text-Guided Diffusion Model
We leverage recent diffusion probabilistic models to generate realistic and diverse synthetic medical image data that preserve the essential characteristics of the original medical images by incorporating edge information of objects to guide the synthesis process.
Instructive Dialogue Summarization with Query Aggregations
With the advancement of instruction-finetuned language models, we introduce instruction-tuning to dialogues to expand the capability set of dialogue summarization models.
Ranked #1 on
Text Summarization
on DialogSum
Tree-Planner: Efficient Close-loop Task Planning with Large Language Models
This paper studies close-loop task planning, which refers to the process of generating a sequence of skills (a plan) to accomplish a specific goal while adapting the plan based on real-time observations.
InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition
We propose InternLM-XComposer, a vision-language large model that enables advanced image-text comprehension and composition.
Ranked #9 on
Visual Question Answering (VQA)
on InfiMM-Eval
Knowledge Graph Embedding: An Overview
We will also discuss an emerging approach for KG completion which leverages pre-trained language models (PLMs) and textual descriptions of entities and relations and offer insights into the integration of KGE embedding methods with PLMs for KG completion.
Deep Mutual Learning across Task Towers for Effective Multi-Task Recommender Learning
Recommender systems usually leverage multi-task learning methods to simultaneously optimize several objectives because of the multi-faceted user behavior data.
Domain Generalization with Fourier Transform and Soft Thresholding
However, it neglects background interference in the amplitude spectrum.
Robust Backdoor Attacks on Object Detection in Real World
However, these models are vulnerable to backdoor attacks.
SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning
We present SeaEval, a benchmark for multilingual foundation models.
What Makes Good Open-Vocabulary Detector: A Disassembling Perspective
A two-stage object detector includes a visual backbone, a region proposal network (RPN), and a region of interest (RoI) head.
AsyncET: Asynchronous Learning for Knowledge Graph Entity Typing with Auxiliary Relations
Previously, KG embedding (KGE) methods tried to solve the KGET task by introducing an auxiliary relation, 'hasType', to model the relationship between entities and their types.
MLLM-DataEngine: An Iterative Refinement Approach for MLLM
Despite the great advance of Multimodal Large Language Models (MLLMs) in both instruction dataset building and benchmarking, the independence of training and evaluation makes current MLLMs hard to further improve their capability under the guidance of evaluation results with a relatively low human cost.
Deep Reinforcement Learning-driven Cross-Community Energy Interaction Optimal Scheduling
In order to coordinate energy interactions among various communities and energy conversions among multi-energy subsystems within the multi-community integrated energy system under uncertain conditions, and achieve overall optimization and scheduling of the comprehensive energy system, this paper proposes a comprehensive scheduling model that utilizes a multi-agent deep reinforcement learning algorithm to learn load characteristics of different communities and make decisions based on this knowledge.
VIGC: Visual Instruction Generation and Correction
A practical solution to this problem would be to utilize the available multimodal large language models (MLLMs) to generate instruction data for vision-language tasks.
Few-Shot Physically-Aware Articulated Mesh Generation via Hierarchical Deformation
By observing an articulated object dataset containing only a few examples, we wish to learn a model that can generate diverse meshes with high visual fidelity and physical validity.
WanJuan: A Comprehensive Multimodal Dataset for Advancing English and Chinese Large Models
The rise in popularity of ChatGPT and GPT-4 has significantly accelerated the development of large models, leading to the creation of numerous impressive large language models(LLMs) and multimodal large language models (MLLMs).
Efficient Multi-View Inverse Rendering Using a Hybrid Differentiable Rendering Method
In this paper, we introduce a novel hybrid differentiable rendering method to efficiently reconstruct the 3D geometry and reflectance of a scene from multi-view images captured by conventional hand-held cameras.
Reconstructed Convolution Module Based Look-Up Tables for Efficient Image Super-Resolution
To enlarge RF with contained LUT sizes, we propose a novel Reconstructed Convolution(RC) module, which decouples channel-wise and spatial calculation.
Impact of UAVs Equipped with ADS-B on the Civil Aviation Monitoring System
However, due to the limited frequency of ADS-B technique, UAVs equipped with ADS-B devices result in the loss of packets to both UAVs and civil aviation.
CMATH: Can Your Language Model Pass Chinese Elementary School Math Test?
We present the Chinese Elementary School Math Word Problems (CMATH) dataset, comprising 1. 7k elementary school-level math word problems with detailed annotations, source from actual Chinese workbooks and exams.
Low-Confidence Samples Mining for Semi-supervised Object Detection
Reliable pseudo-labels from unlabeled data play a key role in semi-supervised object detection (SSOD).
ChiPFormer: Transferable Chip Placement via Offline Decision Transformer
To resolve these challenges, we cast the chip placement as an offline RL formulation and present ChiPFormer that enables learning a transferable placement policy from fixed offline data.
Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization
Naturally, such a paradigm raises three core questions that are not fully answered by prior non-iterative offline RL counterparts like reward-conditioned policy: (q1) What information should we transfer from the inner-level to the outer-level?
Short-Term Voltage Security Constrained UC to Prevent Trip Faults in High Wind Power Penetrated Power Systems
Due to the time delay in WTs' controllers, it is difficult for WTs alone to meet the reactive power demands in different stages of the transient process.
UniMC: A Unified Framework for Long-Term Memory Conversation via Relevance Representation Learning
In this paper, we propose a Unified framework for Long-term Memory Conversations (UniMC), which increases the connection between different stages by learning relevance representation.
Universal Information Extraction with Meta-Pretrained Self-Retrieval
Inspired by the fact that large amount of knowledge are stored in the pretrained language models~(PLM) and can be retrieved explicitly, in this paper, we propose MetaRetriever to retrieve task-specific knowledge from PLMs to enhance universal IE.
Exploring Multi-Timestep Multi-Stage Diffusion Features for Hyperspectral Image Classification
To address this issue, we propose a novel diffusion-based feature learning framework that explores Multi-Timestep Multi-Stage Diffusion features for HSI classification for the first time, called MTMSD.
MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL
Recently, diffusion model shines as a promising backbone for the sequence modeling paradigm in offline reinforcement learning(RL).