Search Results for author:
Found 586 papers, 213 papers with code
The AISP-SJTU Simultaneous Translation System for IWSLT 2022
This paper describes AISP-SJTU’s submissions for the IWSLT 2022 Simultaneous Translation task.
Chinese Opinion Role Labeling with Corpus Translation: A Pivot Study
Opinion Role Labeling (ORL), aiming to identify the key roles of opinion, has received increasing interest.
Syntax in End-to-End Natural Language Processing
This tutorial surveys the latest technical progress of syntactic parsing and the role of syntax in end-to-end natural language processing (NLP) tasks, in which semantic role labeling (SRL) and machine translation (MT) are the representative NLP tasks that have always been beneficial from informative syntactic clues since a long time ago, though the advance from end-to-end deep learning models shows new results.
SJTU-NICT’s Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task
In this paper, we introduced our joint team SJTU-NICT ‘s participation in the WMT 2020 machine translation shared task.
Unsupervised Paraphrasing Consistency Training for Low Resource Named Entity Recognition
Unsupervised consistency training is a way of semi-supervised learning that encourages consistency in model predictions between the original and augmented data.
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.
Few-Shot Class-Incremental Learning for Named Entity Recognition
In this work, we study a more challenging but practical problem, i. e., few-shot class-incremental learning for NER, where an NER model is trained with only few labeled samples of the new classes, without forgetting knowledge of the old ones.
class-incremental learning
Few-Shot Class-Incremental Learning
+4
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.
Chinese Grammatical Error Diagnosis with Graph Convolution Network and Multi-task Learning
For the correction subtask, we utilize the masked language model, the seq2seq model and the spelling check model to generate corrections based on the detection results.
Estimating Q(s,s') with Deterministic Dynamics Gradients
In this paper, we introduce a novel form of a value function, $Q(s, s')$, that expresses the utility of transitioning from a state $s$ to a neighboring state $s'$ and then acting optimally thereafter.
Seed1.5-VL Technical Report
We present Seed1. 5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning.
OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval
The effectiveness of Vision-language RAG systems hinges on multimodal retrieval, which is inherently challenging due to the diverse modalities and knowledge granularities in both queries and knowledge bases.
CachePrune: Neural-Based Attribution Defense Against Indirect Prompt Injection Attacks
In this paper, we propose CachePrune that defends against this attack by identifying and pruning task-triggering neurons from the KV cache of the input prompt context.
PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts
In this paper, we introduce PolyMath, a multilingual mathematical reasoning benchmark covering 18 languages and 4 easy-to-hard difficulty levels.
Step1X-Edit: A Practical Framework for General Image Editing
In recent years, image editing models have witnessed remarkable and rapid development.
Fast-Slow Co-advancing Optimizer: Toward Harmonious Adversarial Training of GAN
Up to now, the training processes of typical Generative Adversarial Networks (GANs) are still particularly sensitive to data properties and hyperparameters, which may lead to severe oscillations, difficulties in convergence, or even failures to converge, especially when the overall variances of the training sets are large.
Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction
Our framework combines the core of traditional SLAM -- bundle adjustment -- with a robust learning-based 3D tracker front-end.
SST: Self-training with self-adaptive thresholding for semi-supervised learning
Semi-supervised learning (SSL) offers a solution to this problem by utilizing a small amount of labeled data along with a large volume of unlabeled data.
Ranked #1 on
Image Classification
on Clothing1M
(using extra training data)
DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
The capacity for complex mathematical reasoning is a key benchmark for artificial intelligence.
Low-Overhead Channel Estimation Framework for Beyond Diagonal Reconfigurable Intelligent Surface Assisted Multi-User MIMO Communication
However, the number of coefficients in the cascaded channels to be estimated in BD-RIS assisted systems is significantly larger than that in conventional RIS assisted systems, because the channels associated with the off-diagonal elements of the scattering matrix have to be estimated as well.
Seedream 3.0 Technical Report
At the data stratum, we double the dataset using a defect-aware training paradigm and a dual-axis collaborative data-sampling framework.
OmniVDiff: Omni Controllable Video Diffusion for Generation and Understanding
In this paper, we propose a novel framework for controllable video diffusion, OmniVDiff, aiming to synthesize and comprehend multiple video visual content in a single diffusion model.
Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model
This technical report highlights the key design decisions that enhance the performance of the medium-sized diffusion model.
SkyReels-A2: Compose Anything in Video Diffusion Transformers
This paper presents SkyReels-A2, a controllable video generation framework capable of assembling arbitrary visual elements (e. g., characters, objects, backgrounds) into synthesized videos based on textual prompts while maintaining strict consistency with reference images for each element.
Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1
Multimodal Large Language Models (MLLMs) inherit this reasoning potential but remain underexplored in tasks requiring both perception and logical reasoning.
Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models
Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to perform complex reasoning tasks, transitioning from fast and intuitive thinking (System 1) to slow and deep reasoning (System 2).
PlatMetaX: An Integrated MATLAB platform for Meta-Black-Box Optimization
The landscape of optimization problems has become increasingly complex, necessitating the development of advanced optimization techniques.
RoCA: Robust Contrastive One-class Time Series Anomaly Detection with Contaminated Data
It fuses the separated assumptions of one-class classification and contrastive learning in a single training process to characterize a more complete so-called normality.
mmTracking: Trajectory Tracking for Uplink mmWave Devices with Multi-Path Doppler Difference of Arrival
There are at least three radio frequency (RF) chains at the BS.
Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
Traditional inference time scaling methods utilize scalar reward signals from process reward models to evaluate candidate reasoning steps, but these scalar rewards lack the nuanced qualitative information essential for understanding and justifying each step.
MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance
However, existing methods struggle with complex object movements and multi-object motion control, resulting in imprecise trajectory adherence, poor object consistency, and compromised visual quality.
Chain of Functions: A Programmatic Pipeline for Fine-Grained Chart Reasoning Data
Employing \textit{CoF}, we construct the \textit{ChartCoF} dataset, with 1. 4k complex reasoning Q\&A for fine-grained analysis and 50k Q\&A for reasoning enhancement.
DAST: Difficulty-Aware Self-Training on Large Language Models
Present Large Language Models (LLM) self-training methods always under-sample on challenging queries, leading to inadequate learning on difficult problems which limits LLMs' ability.
Self-Consistent Equation-guided Neural Networks for Censored Time-to-Event Data
In survival analysis, estimating the conditional survival function given predictors is often of interest.
Multimodal Human-AI Synergy for Medical Imaging Quality Control: A Hybrid Intelligence Framework with Adaptive Dataset Curation and Closed-Loop Evaluation
To address this challenge, in this study, we establish a standardized dataset and evaluation framework for medical imaging QC, systematically assessing large language models (LLMs) in image quality assessment and report standardization.
Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model
The rapid expansion of mobile internet has resulted in a substantial increase in user-generated content (UGC) images, thereby making the thorough assessment of UGC images both urgent and essential.
Ranked #1 on
Image Quality Assessment
on KonIQ-10k
Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens
Recent advancements in large language models (LLMs) have driven significant progress in zero-shot text-to-speech (TTS) synthesis.
Debt Collection Negotiations with Large Language Models: An Evaluation System and Optimizing Decision Making with Multi-Agent
Debt collection negotiations (DCN) are vital for managing non-performing loans (NPLs) and reducing creditor losses.
SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers
We present SkyReels-A1, a simple yet effective framework built upon video diffusion Transformer to facilitate portrait image animation.
Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model
We present Step-Video-T2V, a state-of-the-art text-to-video pre-trained model with 30B parameters and the ability to generate videos up to 204 frames in length.
Graph Federated Learning Based Proactive Content Caching in Edge Computing
With the rapid growth of mobile data traffic and the increasing prevalence of video streaming, proactive content caching in edge computing has become crucial for reducing latency and alleviating network congestion.
From Uncertain to Safe: Conformal Fine-Tuning of Diffusion Models for Safe PDE Control
To address this limitation, we propose Safe Diffusion Models for PDE Control (SafeDiffCon), which introduce the uncertainty quantile as model uncertainty quantification to achieve optimal control under safety constraints through both post-training and inference phases.
Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
To address underthinking, we propose a decoding strategy with thought switching penalty TIP that discourages premature transitions between thoughts, encouraging deeper exploration of each reasoning path.
Towards Robust Incremental Learning under Ambiguous Supervision
Technically, we develop the Prototype-Guided Disambiguation and Replay Algorithm (PGDR) which leverages the class prototypes as a proxy to mitigate two intertwined challenges in IPLL, i. e., label ambiguity and catastrophic forgetting.
Do Large Language Models Truly Understand Geometric Structures?
Geometric ability is a significant challenge for large language models (LLMs) due to the need for advanced spatial comprehension and abstract thinking.
Reinforcement learning Based Automated Design of Differential Evolution Algorithm for Black-box Optimization
To address this challenge, we introduce a novel framework that employs reinforcement learning (RL) to automatically design DE for black-box optimization through meta-learning.
PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented Generation
Despite notable advancements in Retrieval-Augmented Generation (RAG) systems that expand large language model (LLM) capabilities through external retrieval, these systems often struggle to meet the complex and diverse needs of real-world industrial applications.
A Dynamic Improvement Framework for Vehicular Task Offloading
In this paper, the task offloading from vehicles with random velocities is optimized via a novel dynamic improvement framework.
FSMoE: A Flexible and Scalable Training System for Sparse Mixture-of-Experts Models
To enable versatile usage of MoE models, we introduce FSMoE, a flexible training system optimizing task scheduling with three novel techniques: 1) Unified abstraction and online profiling of MoE modules for task scheduling across various MoE implementations.
Neural Honeytrace: A Robust Plug-and-Play Watermarking Framework against Model Extraction Attacks
Guided by the model, we further introduce: (1) a similarity-based training-free watermarking method for plug-and-play and flexible watermarking, and (2) a distribution-based multi-step watermark information transmission strategy for robust watermarking.
How Large is the Universe of RNA-Like Motifs? A Clustering Analysis of RNA Graph Motifs Using Topological Descriptors
To determine which dual graphs in the 99. 89% hypothetical set are more likely to be associated with RNA structures, we apply computational topology descriptors using the Persistent Spectral Graphs (PSG) method to characterize each graph using 19 PSG-based features and use clustering algorithms that partition all possible dual graphs into two clusters, RNA-like cluster and non-RNA-like cluster.
The FACTS Grounding Leaderboard: Benchmarking LLMs' Ability to Ground Responses to Long-Form Input
Models are evaluated using automated judge models in two phases: (1) responses are disqualified if they do not fulfill the user request; (2) they are judged as accurate if the response is fully grounded in the provided document.
M2I2: Learning Efficient Multi-Agent Communication via Masked State Modeling and Intention Inference
To address this issue, we introduce M2I2, a novel framework designed to enhance the agents' capabilities to assimilate and utilize received information effectively.
Is Segment Anything Model 2 All You Need for Surgery Video Segmentation? A Systematic Evaluation
Surgery video segmentation is an important topic in the surgical AI field.
An Experimental Study of Passive UAV Tracking with Digital Arrays and Cellular Downlink Signals
Given the prospects of the low-altitude economy (LAE) and the popularity of unmanned aerial vehicles (UAVs), there are increasing demands on monitoring flying objects at low altitude in wide urban areas.
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
The remarkable performance of models like the OpenAI o1 can be attributed to their ability to emulate human-like long-time thinking during inference.
RobotDiffuse: Motion Planning for Redundant Manipulator based on Diffusion Model
This paper introduces RobotDiffuse, a diffusion model-based approach for motion planning in redundant manipulators.
Modality-Projection Universal Model for Comprehensive Full-Body Medical Imaging Segmentation
The integration of deep learning in medical imaging has shown great promise for enhancing diagnostic, therapeutic, and research outcomes.
Multi-UAV Collaborative Trajectory Planning for Seamless Data Collection and Transmission
Specifically, the mission completion time is minimized by optimizing the trajectories, task allocation, collection time scheduling, and transmission topology of UAVs while ensuring backhaul link to the BS.
UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models
Despite demonstrating impressive capabilities, Large Language Models (LLMs) still often struggle to accurately express the factual knowledge they possess, especially in cases where the LLMs' knowledge boundaries are ambiguous.
StarWhisper Telescope: Agent-Based Observation Assistant System to Approach AI Astrophysicist
Additionally, the integration of AI agents within the system provides online accessibility, saving astronomers' time and encouraging greater participation from amateur astronomers in the NGSS project.
Wavelet Diffusion Neural Operator
Recently, diffusion generative models have emerged as a competitive class of methods for these tasks due to their ability to capture long-term dependencies and model high-dimensional states.
LADDER: Multi-objective Backdoor Attack via Evolutionary Algorithm
Current black-box backdoor attacks in convolutional neural networks formulate attack objective(s) as single-objective optimization problems in single domain.
Draft Model Knows When to Stop: A Self-Verification Length Policy for Speculative Decoding
Speculative Decoding (SD) has become an important technique in accelerating the inference speed of large language models.
SPDFusion: An Infrared and Visible Image Fusion Network Based on a Non-Euclidean Representation of Riemannian Manifolds
Euclidean representation learning methods have achieved commendable results in image fusion tasks, which can be attributed to their clear advantages in handling with linear space.
OpenLS-DGF: An Adaptive Open-Source Dataset Generation Framework for Machine Learning Tasks in Logic Synthesis
This paper introduces OpenLS-DGF, an adaptive logic synthesis dataset generation framework, to enhance machine learning~(ML) applications within the logic synthesis process.
Evolutionary Algorithm with Detection Region Method for Constrained Multi-Objective Problems with Binary Constraints
Solving constrained multi-objective optimization problems (CMOPs) is a challenging task.
Metric Learning for Tag Recommendation: Tackling Data Sparsity and Cold Start Issues
With the rapid growth of digital information, personalized recommendation systems have become an indispensable part of Internet services, especially in the fields of e-commerce, social media, and online entertainment.
ZhoBLiMP: a Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese
Whether and how language models (LMs) acquire the syntax of natural languages has been widely evaluated under the minimal pair paradigm.
Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning
First, we introduce a predictor-corrector learning framework to minimize truncation errors, which consists of a high-order predictor and a multistep corrector.
EnsIR: An Ensemble Algorithm for Image Restoration via Gaussian Mixture Models
We estimate the range-wise ensemble weights on a reference set and store them in a lookup table (LUT) for efficient ensemble inference on the test set.
MovieCharacter: A Tuning-Free Framework for Controllable Character Video Synthesis
Recent advancements in character video synthesis still depend on extensive fine-tuning or complex 3D modeling processes, which can restrict accessibility and hinder real-time applicability.
Weak-to-Strong Preference Optimization: Stealing Reward from Weak Aligned Model
Aligning language models (LMs) with human preferences has become a key area of research, enabling these models to meet diverse user needs better.
A Recommendation Model Utilizing Separation Embedding and Self-Attention for Feature Mining
With the explosive growth of Internet data, users are facing the problem of information overload, which makes it a challenge to efficiently obtain the required resources.
CAPE: A Chinese Dataset for Appraisal-based Emotional Generation using Large Language Models
Generating emotionally appropriate responses in conversations with large language models presents a significant challenge due to the complexities of human emotions and cognitive processes, which remain largely underexplored in their critical role in social interactions.
Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation
LLM self-evaluation relies on the LLM's own ability to estimate response correctness, which can greatly improve its deployment reliability.
MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
This paper addresses this gap by introducing a comprehensive investigation of Multilingual Confidence estimation (MlingConf) on LLMs, focusing on both language-agnostic (LA) and language-specific (LS) tasks to explore the performance and language dominance effects of multilingual confidence estimations on different tasks.
Balancing Innovation and Privacy: Data Security Strategies in Natural Language Processing Applications
By introducing a differential privacy mechanism, our model ensures the accuracy and reliability of data analysis results while adding random noise.
AppBench: Planning of Multiple APIs from Various APPs for Complex User Instruction
In this paper, we introduce \texttt{AppBench}, the first benchmark to evaluate LLMs' ability to plan and execute multiple APIs from various sources in order to complete the user's task.
TLDR: Token-Level Detective Reward Model for Large Vision Language Models
Although reward models have been successful in improving multimodal large language models, the reward models themselves remain brutal and contain minimal information.
Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuning
Achieving consistent high-quality machine translation (MT) across diverse domains remains a significant challenge, primarily due to the limited and imbalanced parallel training data available in various domains.
Segment as You Wish -- Free-Form Language-Based Segmentation for Medical Images
Medical imaging is crucial for diagnosing a patient's health condition, and accurate segmentation of these images is essential for isolating regions of interest to ensure precise diagnosis and treatment planning.
AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference
This demonstrates that AlignSum significantly enhances the alignment of language models with human summarization preferences.
Trajectory Tracking for MmWave Communication Systems via Cooperative Passive Sensing
Specifically, in the uplink communication with at least two transmitters, a cooperative detection method is proposed for the receiver to track the blocker's trajectory, localize the transmitters and detect the potential link blockage jointly.
RMLR: Extending Multinomial Logistic Regression into General Geometries
Specifically, we showcase our framework on the Symmetric Positive Definite (SPD) manifold and special orthogonal group, i. e., the set of rotation matrices.
Harnessing Diversity for Important Data Selection in Pretraining Large Language Models
For each cluster, if we opt to select data from it, we take some samples to evaluate the influence to prevent processing all instances.
Optimizing News Text Classification with Bi-LSTM and Attention Mechanism for Efficient Data Processing
The development of Internet technology has led to a rapid increase in news information.
MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation
Long-term memory is important for chatbots and dialogue systems (DS) to create consistent and human-like conversations, evidenced by numerous developed memory-augmented DS (MADS).
Graph Neural Network Framework for Sentiment Analysis Using Syntactic Feature
Amidst the swift evolution of social media platforms and e-commerce ecosystems, the domain of opinion mining has surged as a pivotal area of exploration within natural language processing.
Context-Conditioned Spatio-Temporal Predictive Learning for Reliable V2V Channel Prediction
Achieving reliable multidimensional Vehicle-to-Vehicle (V2V) channel state information (CSI) prediction is both challenging and crucial for optimizing downstream tasks that depend on instantaneous CSI.
DCMAC: Demand-aware Customized Multi-Agent Communication via Upper Bound Training
Efficient communication can enhance the overall performance of collaborative multi-agent reinforcement learning.
Untie the Knots: An Efficient Data Augmentation Strategy for Long-Context Pre-Training in Language Models
Large language models (LLM) have prioritized expanding the context window from which models can incorporate more information.
GALLa: Graph Aligned Large Language Models for Improved Source Code Understanding
Programming languages possess rich semantic information such as data flow that is represented by graphs and not available from the surface form of source code.
Fast Capacity Estimation in Ultra-dense Wireless Networks with Random Interference
In ultra-dense wireless networks with extremely large numbers of base stations (BSs) and users, we provide fast estimation methods for determining the capacity.
A Hybrid Transformer-Mamba Network for Single Image Deraining
Existing deraining Transformers employ self-attention mechanisms with fixed-range windows or along channel dimensions, limiting the exploitation of non-local receptive fields.
MakeupAttack: Feature Space Black-box Backdoor Attack on Face Recognition via Makeup Transfer
Furthermore, due to the perceptibility, diversity, and similarity of facial datasets, many state-of-the-art backdoor attacks lose effectiveness on face recognition tasks.
Fostering Natural Conversation in Large Language Models with NICO: a Natural Interactive COnversation dataset
Benefiting from diverse instruction datasets, contemporary Large Language Models (LLMs) perform effectively as AI assistants in collaborating with humans.
PITN: Physics-Informed Temporal Networks for Cuffless Blood Pressure Estimation
To tackle this challenge, we introduce a novel physics-informed temporal network~(PITN) with adversarial contrastive learning to enable precise BP estimation with very limited data.
Sparse Deep Learning Models with the $\ell_1$ Regularization
Sparse neural networks are highly desirable in deep learning in reducing its complexity.
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #3 on
Question Answering
on PeerQA
FTuner: A Fast Dynamic Shape Tensors Program Auto-Tuner for Deep Learning Compilers
Instead of using a large design space or training a cost model, we use an abstract computational unit called the uKernel to patch together small, various-sized tensors to match the shape of the input tensor.
Relaxed Equivariant Graph Neural Networks
3D Euclidean symmetry equivariant neural networks have demonstrated notable success in modeling complex physical systems.
Longhorn: State Space Models are Amortized Online Learners
Our experimental results show that Longhorn outperforms state-of-the-art SSMs, including the Mamba model, on standard sequence modeling benchmarks, language modeling, and vision tasks.
Restoring Images in Adverse Weather Conditions via Histogram Transformer
It is powered by a mechanism dubbed histogram self-attention, which sorts and segments spatial features into intensity-based bins.
DiffPhyCon: A Generative Approach to Control Complex Physical Systems
In this work, we introduce Diffusion Physical systems Control (DiffPhyCon), a new class of method to address the physical systems control problem.
Evaluating Knowledge-based Cross-lingual Inconsistency in Large Language Models
This paper investigates the cross-lingual inconsistencies observed in Large Language Models (LLMs), such as ChatGPT, Llama, and Baichuan, which have shown exceptional performance in various Natural Language Processing (NLP) tasks.
FAFE: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group Frames
Despite the striking success of general protein folding models such as AlphaFold2(AF2, Jumper et al. (2021)), the accurate computational modeling of antibody-antigen complexes remains a challenging task.
Feature-prompting GBMSeg: One-Shot Reference Guided Training-Free Prompt Engineering for Glomerular Basement Membrane Segmentation
Experimental results on our collected 2538 TEM images confirm that GBMSeg achieves superior segmentation performance with a Dice similarity coefficient (DSC) of 87. 27% using only one labeled reference image in a training-free manner, outperforming recently proposed one-shot or few-shot methods.
Multimodal Physiological Signals Representation Learning via Multiscale Contrasting for Depression Recognition
Furthermore, to enhance the learning of semantic representation associated with stimulation tasks, a semantic consistency contrast module is proposed, aiming to maximize the semantic similarity of fNIRS and EEG.
DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving
Solving mathematical problems requires advanced reasoning abilities and presents notable challenges for large language models.
Ranked #4 on
Natural Questions
on TheoremQA
(using extra training data)
Balancing Performance and Cost for Two-Hop Cooperative Communications: Stackelberg Game and Distributed Multi-Agent Reinforcement Learning
This paper aims to balance performance and cost in a two-hop wireless cooperative communication network where the source and relays have contradictory optimization goals and make decisions in a distributed manner.
On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey
Within the evolving landscape of deep learning, the dilemma of data quantity and quality has been a long-standing problem.
EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts
Recent advancements in image generation have enabled the creation of high-quality images from text conditions.
Asynchronous Voice Anonymization Using Adversarial Perturbation On Speaker Embedding
Voice anonymization has been developed as a technique for preserving privacy by replacing the speaker's voice in a speech signal with that of a pseudo-speaker, thereby obscuring the original voice attributes from machine recognition and human perception.
Triage of 3D pathology data via 2.5D multiple-instance learning to guide pathologist assessments
A potential early route towards clinical adoption for 3D pathology is to rely on pathologists for final diagnosis based on viewing familiar 2D H&E-like image sections from the 3D datasets.
Fast-Fading Channel and Power Optimization of the Magnetic Inductive Cellular Network
Finally, we propose the power control algorithm using the non-cooperative game and multiagent Q-learning methods to optimize the throughput of the cellular VMI network.
Graph Neural Network Enhanced Retrieval for Question Answering of LLMs
A graph neural network (GNN) is then leveraged to exploit the relationships between passages and improve the retrieval of supporting passages.
A Recipe for Charge Density Prediction
In density functional theory, charge density is the core attribute of atomic systems from which all chemical properties can be derived.
Floor-Plan-aided Indoor Localization: Zero-Shot Learning Framework, Data Sets, and Prototype
Specifically, a graph neural network that is scalable to the number of access points (APs) and mobile devices (MDs) is used for obtaining coarse locations of MDs.
Ultra-Fast Adaptive Track Detection Network
Compared to the SOTA, the proposed model is competitive in both speed and accuracy.
Embedding Trajectory for Out-of-Distribution Detection in Mathematical Reasoning
Real-world data deviating from the independent and identically distributed (i. i. d.)
When Large Language Model Meets Optimization
Optimization algorithms and large language models (LLMs) enhance decision-making in dynamic environments by integrating artificial intelligence with traditional techniques.
Dual-Segment Clustering Strategy for Hierarchical Federated Learning in Heterogeneous Wireless Environments
Non-independent and identically distributed (Non- IID) data adversely affects federated learning (FL) while heterogeneity in communication quality can undermine the reliability of model parameter transmission, potentially degrading wireless FL convergence.
ReinWiFi: A Reinforcement-Learning-Based Framework for the Application-Layer QoS Optimization of WiFi Networks
In this paper, a reinforcement-learning-based scheduling framework is proposed and implemented to optimize the application-layer quality-of-service (QoS) of a practical wireless local area network (WLAN) suffering from unknown interference.
A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges
From the analysis and evaluation results, we identify key challenges and offer principles for future research to enhance the design of models and frameworks in the dynamic GNNs field.
PAD: Patch-Agnostic Defense against Adversarial Patch Attacks
Adversarial patch attacks present a significant threat to real-world object detectors due to their practical feasibility.
Nyonic Technical Report
This report details the development and key achievements of our latest language model designed for custom large language models.
Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs
Chain-of-Thought (CoT) has been a widely adopted prompting method, eliciting impressive reasoning abilities of Large Language Models (LLMs).
SNR Maximization and Localization for UAV-IRS-Assisted Near-Field Systems
This letter introduces a novel unmanned aerial vehicle (UAV)-intelligent reflecting surface (IRS) structure into near-field localization systems to enhance the design flexibility of IRS, thereby obtaining additional performance gains.
Rechargeable UAV Trajectory Optimization for Real-Time Persistent Data Collection of Large-Scale Sensor Networks
In this paper, we propose a rechargeable UAV-assisted periodic data collection scheme, where a UAV is dispatched to periodically collect data from sensor nodes (SNs) in the mission area and charged by a wireless charging platform.
Research on OPF control of three-phase four-wire low-voltage distribution network considering uncertainty
As power systems become more complex and uncertain, low-voltage distribution networks face numerous challenges, including three-phase imbalances caused by asymmetrical loads and distributed energy resources.
A SER-based Device Selection Mechanism in Multi-bits Quantization Federated Learning
The quality of wireless communication will directly affect the performance of federated learning (FL), so this paper analyze the influence of wireless communication on FL through symbol error rate (SER).
AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation
Adversarial example detection, which can be conveniently applied in many scenarios, is important in the area of adversarial defense.
The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data
This inspires us to propose a novel dual-network training framework: The Victim and The Beneficiary (V&B), which exploits a poisoned model to train a clean model without extra benign samples.
Cross-Modality Gait Recognition: Bridging LiDAR and Camera Modalities for Human Identification
Current gait recognition research mainly focuses on identifying pedestrians captured by the same type of sensor, neglecting the fact that individuals may be captured by different sensors in order to adapt to various environments.
Embedding-Informed Adaptive Retrieval-Augmented Generation of Large Language Models
However, it was observed by previous works that retrieval is not always helpful, especially when the LLM is already knowledgeable on the query to answer.
Interpretable Multi-View Clustering Based on Anchor Graph Tensor Factorization
Nevertheless, existing multi-view clustering methods based on anchor graph factorization lack adequate cluster interpretability for the decomposed matrix and often overlook the inter-view information.
Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs
The Large Language Model (LLM) is widely employed for tasks such as intelligent assistants, text summarization, translation, and multi-modality on mobile phones.
Enhanced Short Text Modeling: Leveraging Large Language Models for Topic Refinement
Crafting effective topic models for brief texts, like tweets and news headlines, is essential for capturing the swift shifts in social dynamics.
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)
Towards Human-Like Machine Comprehension: Few-Shot Relational Learning in Visually-Rich Documents
This approach aims to generate relation representations that are more aware of the spatial context and unseen relation in a manner similar to human perception.
AVT2-DWF: Improving Deepfake Detection with Audio-Visual Fusion and Dynamic Weighting Strategies
With the continuous improvements of deepfake methods, forgery messages have transitioned from single-modality to multi-modal fusion, posing new challenges for existing forgery detection algorithms.
VXP: Voxel-Cross-Pixel Large-scale Image-LiDAR Place Recognition
To tackle this issue, we propose Voxel-Cross-Pixel (VXP), a novel camera-to-LiDAR place recognition framework that enforces local similarities in a self-supervised manner and effectively brings global context from images and LiDAR scans into a shared feature space.
AffineQuant: Affine Transformation Quantization for Large Language Models
Among these techniques, Post-Training Quantization (PTQ) has emerged as a subject of considerable interest due to its noteworthy compression efficiency and cost-effectiveness in the context of training.
StableGarment: Garment-Centric Generation via Stable Diffusion
In this paper, we introduce StableGarment, a unified framework to tackle garment-centric(GC) generation tasks, including GC text-to-image, controllable GC text-to-image, stylized GC text-to-image, and robust virtual try-on.
ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
Diffusion models have demonstrated remarkable performance in the domain of text-to-image generation.
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
In this report, we introduce the Gemini 1. 5 family of models, representing the next generation of highly compute-efficient multimodal models capable of recalling and reasoning over fine-grained information from millions of tokens of context, including multiple long documents and hours of video and audio.
RIS-empowered Topology Control for Distributed Learning in Urban Air Mobility
Urban Air Mobility (UAM) expands vehicles from the ground to the near-ground space, envisioned as a revolution for transportation systems.
F$^3$Loc: Fusion and Filtering for Floorplan Localization
In this paper we propose an efficient data-driven solution to self-localization within a floorplan.
Drug Resistance Predictions Based on a Directed Flag Transformer
CAPTURE combines a comprehensive mutation analysis with a resistance prediction module based on DFFormer-seq, which is a novel ensemble model that leverages a new Directed Flag Transformer and sequence embeddings from the protein and small-molecule-large-language models.
Hypothesis Spaces for Deep Learning
The representer theorems unfold that solutions of these learning models can be expressed as linear combination of a finite number of kernel sessions determined by given data and the reproducing kernel.
Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models
2) Role Prompting assigns a central prompt to the general domain and a unique role prompt to each specific domain to minimize inter-domain confusion during training.
Logit Standardization in Knowledge Distillation
Knowledge distillation involves transferring soft labels from a teacher to a student using a shared temperature-based softmax function.
Ranked #2 on
Knowledge Distillation
on CIFAR-100
Mitigating Reversal Curse in Large Language Models via Semantic-aware Permutation Training
Accordingly, permutation on the training data is considered as a potential solution, since this can make the model predict antecedent words or tokens.
Beyond Language Models: Byte Models are Digital World Simulators
Traditional deep learning often overlooks bytes, the basic units of the digital world, where all forms of information and operations are encoded and manipulated in binary format.
WanJuan-CC: A Safe and High-Quality Open-sourced English Webtext Dataset
To evaluate the quality and utility of the dataset, we trained 1B-parameter and 3B-parameter models using WanJuan-CC and another dataset, RefinedWeb.
Improving Open-Ended Text Generation via Adaptive Decoding
Current language models decode text token by token according to probabilistic distribution, and determining the appropriate candidates for the next token is crucial to ensure generation quality.
UniRetriever: Multi-task Candidates Selection for Various Context-Adaptive Conversational Retrieval
Conversational retrieval refers to an information retrieval system that operates in an iterative and interactive manner, requiring the retrieval of various external resources, such as persona, knowledge, and even response, to effectively engage with the user and successfully complete the dialogue.
Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method
Bargaining is an important and unique part of negotiation between humans.
Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm
Extensive experiments on real-world datasets verify the effectiveness and robustness of LFBA against image processing operations and the state-of-the-art backdoor defenses, as well as its inherent stealthiness in both spatial and frequency space, making it resilient against frequency inspection.
Is Self-knowledge and Action Consistent or Not: Investigating Large Language Model's Personality
In this study, we delve into the validity of conventional personality questionnaires in capturing the human-like personality traits of Large Language Models (LLMs).
Can Watermarks Survive Translation? On the Cross-lingual Consistency of Text Watermark for Large Language Models
Furthermore, we analyze two key factors that contribute to the cross-lingual consistency in text watermarking and propose X-SIR as a defense method against CWRA.
A Comprehensive Study of Multilingual Confidence Estimation on Large Language Models
This paper addresses this gap by introducing a comprehensive investigation of Multilingual Confidence estimation (MlingConf) on LLMs, focusing on both language-agnostic (LA) and language-specific (LS) tasks to explore the performance and language dominance effects of multilingual confidence estimations on different tasks.
Unsupervised Sign Language Translation and Generation
Motivated by the success of unsupervised neural machine translation (UNMT), we introduce an unsupervised sign language translation and generation network (USLNet), which learns from abundant single-modality (text and video) data without parallel sign language data.
A Novel Paradigm in Solving Multiscale Problems
By enabling the acquisition of large-scale data with minimal computational demands, coupled with the efficient and accurate characterization of small-scale dynamics via Spectral PINN, our approach offers a valuable and promising approach for researchers seeking to tackle multiscale phenomena effectively.
Partial Identification of Binary Choice Models with Misreported Outcomes
In the first approach, the instrument is assumed to only affect the true dependent variable but not misreporting probabilities.
UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems
To better plan and incorporate the use of multiple sources in generating personalized response, we firstly decompose it into three sub-tasks: Knowledge Source Selection, Knowledge Retrieval, and Response Generation.
Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Model
In this work, we investigate the potential of employing the QE model as the reward model to predict human preferences for feedback training.
T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integration
This process enables agents to collectively use evidence garnered from multiple perspectives, fostering trusted and cooperative behaviors.
R-Judge: Benchmarking Safety Risk Awareness for LLM Agents
We introduce R-Judge, a benchmark crafted to evaluate the proficiency of LLMs in judging and identifying safety risks given agent interaction records.
DiffusionGPT: LLM-Driven Text-to-Image Generation System
Diffusion models have opened up new avenues for the field of image generation, resulting in the proliferation of high-quality models shared on open-source platforms.
Passive Beamforming For Practical RIS-Assisted Communication Systems With Non-Ideal Hardware
Reconfigurable intelligent surface (RIS) technology is a promising solution to improve the performance of existing wireless communications.
Toward distortion-aware change detection in realistic scenarios
The whole framework is composed of Pretext Representation Pre-training, Bitemporal Image Alignment, and Down-stream Decoder Fine-Tuning.
LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry
Visual odometry estimates the motion of a moving camera based on visual input.
SEED-Bench: Benchmarking Multimodal Large Language Models
Multimodal large language models (MLLMs) building upon the foundation of powerful large language models (LLMs) have recently demonstrated exceptional capabilities in generating not only texts but also images given interleaved multimodal inputs (acting like a combination of GPT-4V and DALL-E 3).
F3Loc: Fusion and Filtering for Floorplan Localization
In this paper we propose an efficient data-driven solution to self-localization within a floorplan.
Boosting Large Language Model for Speech Synthesis: An Empirical Study
In this paper, we conduct a comprehensive empirical exploration of boosting LLMs with the ability to generate speech, by combining pre-trained LLM LLaMA/OPT and text-to-speech synthesis model VALL-E. We compare three integration methods between LLMs and speech synthesis models, including directly fine-tuned LLMs, superposed layers of LLMs and VALL-E, and coupled LLMs and VALL-E using LLMs as a powerful text encoder.
Identification of Nonlinear Dynamic Panels under Partial Stationarity
This paper studies identification for a wide range of nonlinear panel data models, including binary choice, ordered response, and other types of limited dependent variable models.
Exploring 3D-aware Lifespan Face Aging via Disentangled Shape-Texture Representations
Existing face aging methods often focus on modeling either texture aging or using an entangled shape-texture representation to achieve face aging.
SSR-Encoder: Encoding Selective Subject Representation for Subject-Driven Generation
Recent advancements in subject-driven image generation have led to zero-shot generation, yet precise selection and focus on crucial subject representations remain challenging.
Reconfigurable Intelligent Surface-Assisted Localization in OFDM Systems with Carrier Frequency Offset and Phase Noise
The localization accuracy of the proposed algorithm is close to the analytical lower bound, with a root mean square error of lower than $\rm 10^{-2} \: m$.
Rethinking Dimensional Rationale in Graph Contrastive Learning from Causal Perspective
To this end, with the purpose of exploring the intrinsic rationale of graphs, we accordingly propose to capture the dimensional rationale from graphs, which has not received sufficient attention in the literature.
Transferring CLIP's Knowledge into Zero-Shot Point Cloud Semantic Segmentation
In this work, we focus on zero-shot point cloud semantic segmentation and propose a simple yet effective baseline to transfer the visual-linguistic knowledge implied in CLIP to point cloud encoder at both feature and output levels.
Vision-language Assisted Attribute Learning
Attribute labeling at large scale is typically incomplete and partial, posing significant challenges to model optimization.
DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting
A unified and flexible framework that can equip any type of spatio-temporal models is proposed based on residual diffusion, which effectively tackles the shortcomings of previous methods.
EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning
The pursuit of artificial general intelligence (AGI) has been accelerated by Multimodal Large Language Models (MLLMs), which exhibit superior reasoning, generalization capabilities, and proficiency in processing multimodal inputs.
Unsupervised Social Event Detection via Hybrid Graph Contrastive Learning and Reinforced Incremental Clustering
To this end, recent works explore learning discriminative information from social messages by leveraging graph contrastive learning (GCL) and embedding clustering in an unsupervised manner.
Multi-scale Residual Transformer for VLF Lightning Transients Classification
The utilization of Very Low Frequency (VLF) electromagnetic signals in navigation systems is widespread.
FaceStudio: Put Your Face Everywhere in Seconds
This study investigates identity-preserving image synthesis, an intriguing task in image generation that seeks to maintain a subject's identity while adding a personalized, stylistic touch.
VIoTGPT: Learning to Schedule Vision Tools in LLMs towards Intelligent Video Internet of Things
Video Internet of Things (VIoT) has shown full potential in collecting an unprecedented volume of video data.
SEED-Bench-2: Benchmarking Multimodal Large Language Models
Multimodal large language models (MLLMs), building upon the foundation of powerful large language models (LLMs), have recently demonstrated exceptional capabilities in generating not only texts but also images given interleaved multimodal inputs (acting like a combination of GPT-4V and DALL-E 3).
Riemannian Self-Attention Mechanism for SPD Networks
Symmetric positive definite (SPD) matrix has been demonstrated to be an effective feature descriptor in many scientific areas, as it can encode spatiotemporal statistics of the data adequately on a curved Riemannian manifold, i. e., SPD manifold.
Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning
We conduct extensive experiments on various benchmarks, including a dataset with large-scale tasks, and compare our method against some recent state-of-the-art methods to demonstrate the effectiveness and scalability of our proposed method.
RetroDiff: Retrosynthesis as Multi-stage Distribution Interpolation
Our key innovation is to develop a multi-stage diffusion process.
Igniting Language Intelligence: The Hitchhiker's Guide From Chain-of-Thought Reasoning to Language Agents
Large language models (LLMs) have dramatically enhanced the field of language intelligence, as demonstrably evidenced by their formidable empirical performance across a spectrum of complex reasoning tasks.
MELA: Multilingual Evaluation of Linguistic Acceptability
In this work, we present the largest benchmark to date on linguistic acceptability: Multilingual Evaluation of Linguistic Acceptability -- MELA, with 46K samples covering 10 languages from a diverse set of language families.
CLEAN-EVAL: Clean Evaluation on Contaminated Large Language Models
The best candidate is finally selected from this set based on the BLEURT score.
Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code
In this work we systematically review the recent advancements in software engineering with language models, covering 70+ models, 40+ evaluation tasks, 180+ datasets, and 900 related works.
