Search Results for author:
Found 74 papers, 29 papers with code
Towards Making the Most of Cross-Lingual Transfer for Zero-Shot Neural Machine Translation
When applied to zero-shot cross-lingual abstractive summarization, it produces an average performance gain of 12. 3 ROUGE-L over mBART-ft. We conduct detailed analyses to understand the key ingredients of SixT+, including multilinguality of the auxiliary parallel data, positional disentangled encoder, and the cross-lingual transferability of its encoder.
Abstractive Text Summarization
Cross-Lingual Abstractive Summarization
+6
Towards Bridging the Reward-Generation Gap in Direct Alignment Algorithms
In this paper, we find a contributor to the reward-generation gap is the mismatch between the inherent importance of prefix tokens during the LLM generation process and how this importance is reflected in the implicit reward functions of DAAs.
Pi-SQL: Enhancing Text-to-SQL with Fine-Grained Guidance from Pivot Programming Languages
In this work, we propose Pi-SQL, which incorporates the high-resource Python program as a pivot to bridge between the natural language query and SQL program.
AudioTurbo: Fast Text-to-Audio Generation with Rectified Diffusion
Diffusion models have significantly improved the quality and diversity of audio generation but are hindered by slow inference speed.
TAG-INSTRUCT: Controlled Instruction Complexity Enhancement through Structure-based Augmentation
High-quality instruction data is crucial for developing large language models (LLMs), yet existing approaches struggle to effectively control instruction complexity.
ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs
With the proliferation of task-specific large language models, delta compression has emerged as a method to mitigate the resource challenges of deploying numerous such models by effectively compressing the delta model parameters.
Fin-R1: A Large Language Model for Financial Reasoning through Reinforcement Learning
Reasoning large language models are rapidly evolving across various domains.
A Hybrid Model/Data-Driven Solution to Channel, Position and Orientation Tracking in mmWave Vehicular Systems
A second network named VP-ChAT (Vehicle Position-Channel Attention for position Tracking) refines the geometric position estimate.
LayAlign: Enhancing Multilingual Reasoning in Large Language Models via Layer-Wise Adaptive Fusion and Alignment Strategy
Despite being pretrained on multilingual corpora, large language models (LLMs) exhibit suboptimal performance on low-resource languages.
GenAssets: Generating in-the-wild 3D Assets in Latent Space
High-quality 3D assets for traffic participants are critical for multi-sensor simulation, which is essential for the safe end-to-end development of autonomy.
Revisiting Generative Policies: A Simpler Reinforcement Learning Algorithmic Perspective
However, existing works exhibit significant variations in training schemes and RL optimization objectives, and some methods are only applicable to diffusion models.
Compound-QA: A Benchmark for Evaluating LLMs on Compound Questions
In this paper, we introduce Compound Question Synthesis (CQ-Syn) to create the Compound-QA benchmark, focusing on compound questions with multiple sub-questions.
TSI: A Multi-View Representation Learning Approach for Time Series Forecasting
As the growing demand for long sequence time-series forecasting in real-world applications, such as electricity consumption planning, the significance of time series forecasting becomes increasingly crucial across various domains.
G3R: Gradient Guided Generalizable Reconstruction
Large scale 3D scene reconstruction is important for applications such as virtual reality and simulation.
Deconfounding Multi-Cause Latent Confounders: A Factor-Model Approach to Climate Model Bias Correction
This paper proposes a novel bias correction approach to utilize both GCM and observational data to learn a factor model that captures multi-cause latent confounders.
SeqAR: Jailbreak LLMs with Sequential Auto-Generated Characters
The widespread applications of large language models (LLMs) have brought about concerns regarding their potential misuse.
SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation
In this work, we propose SeTAR, a novel, training-free OOD detection method that leverages selective low-rank approximation of weight matrices in vision-language and vision-only models.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
Motivated by the long-tail distribution of singular values in the delta weights, we propose a delta quantization approach using mixed-precision.
MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning
It is observed that the minor matrix corresponds to the noisy or long-tail information, while the principal matrix contains important knowledge.
Multi-level Personalized Federated Learning on Heterogeneous and Long-Tailed Data
Federated learning (FL) offers a privacy-centric distributed learning framework, enabling model training on individual clients and central aggregation without necessitating data exchange.
CSST Strong Lensing Preparation: a Framework for Detecting Strong Lenses in the Multi-color Imaging Survey by the China Survey Space Telescope (CSST)
To overcome these challenges, we have developed a framework based on a hierarchical visual Transformer with a sliding window technique to search for strong lensing systems within entire images.
Distract Large Language Models for Automatic Jailbreak Attack
Extensive efforts have been made before the public release of Large language models (LLMs) to align their behaviors with human values.
OMGEval: An Open Multilingual Generative Evaluation Benchmark for Large Language Models
We evaluate several representative multilingual LLMs on the proposed OMGEval, which we believe will provide a valuable reference for the community to further understand and improve the multilingual capability of LLMs.
LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks
Most prior works on LoRA combination primarily rely on task-level weights for each involved LoRA, making different examples and tokens share the same LoRA weights.
Attention-based Interactive Disentangling Network for Instance-level Emotional Voice Conversion
We introduce a two-stage pipeline to effectively train our network: Stage I utilizes inter-speech contrastive learning to model fine-grained emotion and intra-speech disentanglement learning to better separate emotion and content.
LightSim: Neural Lighting Simulation for Urban Scenes
Different outdoor illumination conditions drastically alter the appearance of urban scenes, and they can harm the performance of image-based robot perception systems if not seen during training.
Reconstructing Objects in-the-wild for Realistic Sensor Simulation
In this work, we present NeuSim, a novel approach that estimates accurate geometry and realistic appearance from sparse in-the-wild data captured at distance and at limited viewpoints.
Real-Time Neural Rasterization for Large Scenes
We propose a new method for realistic real-time novel-view synthesis (NVS) of large scenes.
CADSim: Robust and Scalable in-the-wild 3D Reconstruction for Controllable Sensor Simulation
To tackle these issues, we present CADSim, which combines part-aware object-class priors via a small set of CAD models with differentiable rendering to automatically reconstruct vehicle geometry, including articulated wheels, with high-quality appearance.
StyleBART: Decorate Pretrained Model with Style Adapters for Unsupervised Stylistic Headline Generation
Stylistic headline generation is the task to generate a headline that not only summarizes the content of an article, but also reflects a desired style that attracts users.
PACIT: Unlocking the Power of Examples for Better In-Context Instruction Tuning
Instruction tuning enhances the instruction following ability of large language models by finetuning with supervised instruction data.
Sparse Recovery with Attention: A Hybrid Data/Model Driven Solution for High Accuracy Position and Channel Tracking at mmWave
In this paper, we propose first a mmWave channel tracking algorithm based on multidimensional orthogonal matching pursuit algorithm (MOMP) using reduced sparsifying dictionaries, which exploits information from channel estimates in previous frames.
FinEval: A Chinese Financial Domain Knowledge Evaluation Benchmark for Large Language Models
The dataset contains 8, 351 questions categorized into four different key areas: Financial Academic Knowledge, Financial Industry Knowledge, Financial Security Knowledge, and Financial Agent.
UniSim: A Neural Closed-Loop Sensor Simulator
Previously recorded driving logs provide a rich resource to build these new scenarios from, but for closed loop evaluation, we need to modify the sensor data based on the new scene configuration and the SDV's decisions, as actors might be added or removed and the trajectories of existing actors and the SDV will differ from the original log.
Target Search and Navigation in Heterogeneous Robot Systems with Deep Reinforcement Learning
Collaborative heterogeneous robot systems can greatly improve the efficiency of target search and navigation tasks.
mCLIP: Multilingual CLIP via Cross-lingual Transfer
Furthermore, to enhance the token- and sentence-level multilingual representation of the MTE, we propose to train it with machine translation and contrastive learning jointly before the TriKD to provide a better initialization.
Learning to Localize with Attention: from sparse mmWave channel estimates from a single BS to high accuracy 3D location
One strategy to obtain user location information in a wireless network operating at millimeter wave (mmWave) is based on the exploitation of the geometric relationships between the channel parameters and the user position.
Multilingual Sentence Transformer as A Multilingual Word Aligner
In this paper, we investigate whether multilingual sentence Transformer LaBSE is a strong multilingual word aligner.
Lexical Complexity Controlled Sentence Generation
Compared with potential solutions, our approach fuses the representations of the word complexity levels into the model to get better control of lexical complexity.
RIS-ADMM: A RIS and ADMM-Based Passive and Sparse Sensing Method With Interference Removal
This letter addresses the passive sensing issue utilizing wireless communication signals and RIS amidst interference from wireless access points (APs).
LitMind Dictionary: An Open-Source Online Dictionary
Since traditional dictionaries present word senses as discrete items in predefined inventories, they fall short of flexibility, which is required in providing specific meanings of words in particular contexts.
PrivateRec: Differentially Private Training and Serving for Federated News Recommendation
Collecting and training over sensitive personal data raise severe privacy concerns in personalized recommendation systems, and federated learning can potentially alleviate the problem by training models over decentralized user data. However, a theoretically private solution in both the training and serving stages of federated recommendation is essential but still lacking. Furthermore, naively applying differential privacy (DP) to the two stages in federated recommendation would fail to achieve a satisfactory trade-off between privacy and utility due to the high-dimensional characteristics of model gradients and hidden representations. In this work, we propose a federated news recommendation method for achieving a better utility in model training and online serving under a DP guarantee. We first clarify the DP definition over behavior data for each round in the life-circle of federated recommendation systems. Next, we propose a privacy-preserving online serving mechanism under this definition based on the idea of decomposing user embeddings with public basic vectors and perturbing the lower-dimensional combination coefficients.
Joint Initial Access and Localization in Millimeter Wave Vehicular Networks: a Hybrid Model/Data Driven Approach
High resolution compressive channel estimation provides information for vehicle localization when a hybrid mmWave MIMO system is considered.
Multitasking Framework for Unsupervised Simple Definition Generation
We demonstrate that the framework can generate relevant, simple definitions for the target words through automatic and manual evaluations on English and Chinese datasets.
SDOA-Net: An Efficient Deep Learning-Based DOA Estimation Network for Imperfect Array
The estimation of direction of arrival (DOA) is a crucial issue in conventional radar, wireless communication, and integrated sensing and communication (ISAC) systems.
Deep Learning-based Link Configuration for Radar-aided Multiuser mmWave Vehicle-to-Infrastructure Communication
Then, a deep network is used to translate features of these radar spatial covariances into features of the communication spatial covariances, by learning the intricate mapping between radar and communication channels, in both line-of-sight and non-line-of-sight settings.
YACLC: A Chinese Learner Corpus with Multidimensional Annotation
This resource is of great relevance for second language acquisition research, foreign-language teaching, and automatic grammatical error correction.
Radar Aided mmWave Vehicle-to-InfrastructureLink Configuration Using Deep Learning
In this paper, we obtain prior information to speed up the beam training process by implementing two deep neural networks (DNNs) that realize radar-to-communication (R2C) channel information translation in a vehicle-to-infrastructure (V2I) system.
Towards Making the Most of Multilingual Pretraining for Zero-Shot Neural Machine Translation
When applied to zero-shot cross-lingual abstractive summarization, it produces an average performance gain of 12. 3 ROUGE-L over mBART-ft. We conduct detailed analyses to understand the key ingredients of SixT+, including multilinguality of the auxiliary parallel data, positional disentangled encoder, and the cross-lingual transferability of its encoder.
Abstractive Text Summarization
Cross-Lingual Abstractive Summarization
+6
Zero-shot Cross-lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoders
In this paper, we focus on a zero-shot cross-lingual transfer task in NMT.
Multi-Scale Feature Pyramid Network: A Heavily Occluded Pedestrian Detection Network Based on ResNet
MFPN includes two modules, namely double feature pyramid network (FPN) integrated with ResNet (DFR) and repulsion loss of minimum (RLM).
Few-Shot Domain Adaptation for Grammatical Error Correction via Meta-Learning
We exploit a set of data-rich source domains to learn the initialization of model parameters that facilitates fast adaptation on new resource-poor target domains.
Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving
Yet, there have been limited studies on the adversarial robustness of multi-modal models that fuse LiDAR features with image features.
GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving
Scalable sensor simulation is an important yet challenging open problem for safety-critical domains such as self-driving.
Learning Joint 2D-3D Representations for Depth Completion
In this paper, we tackle the problem of depth completion from RGBD data.
Multi-Task Multi-Sensor Fusion for 3D Object Detection
In this paper we propose to exploit multiple related tasks for accurate multi-sensor 3D object detection.
Ranked #14 on
3D Object Detection
on KITTI Cars Easy
Toward Cross-Lingual Definition Generation for Language Learners
We demonstrate the effectiveness of this approach on zero-shot definition generation.
DSDNet: Deep Structured self-Driving Network
In this paper, we propose the Deep Structured self-Driving Network (DSDNet), which performs object detection, motion prediction, and motion planning with a single neural network.
Learning Lane Graph Representations for Motion Forecasting
We propose a motion forecasting model that exploits a novel structured map representation as well as actor-map interactions.
PnPNet: End-to-End Perception and Prediction with Tracking in the Loop
We tackle the problem of joint perception and motion forecasting in the context of self-driving vehicles.
A Deep Reinforcement Learning Approach to Efficient Drone Mobility Support
In this paper, we propose a novel handover framework for providing efficient mobility support and reliable wireless connectivity to drones served by a terrestrial cellular network.
Accurate Word Alignment Induction from Neural Machine Translation
Shift-Att is an interpretation method that induces alignments from the attention weights of Transformer and does not require parameter update or architecture change.
Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT
However, this approach of evaluating a language model is undermined by the uncertainty of the amount of knowledge that is learned by the probe itself.
Dictionary-based Data Augmentation for Cross-Domain Neural Machine Translation
Existing data augmentation approaches for neural machine translation (NMT) have predominantly relied on back-translating in-domain (IND) monolingual corpora.
Efficient Drone Mobility Support Using Reinforcement Learning
Flying drones can be used in a wide range of applications and services from surveillance to package delivery.
A General Framework for Adaptation of Neural Machine Translation to Simultaneous Translation
Despite the success of neural machine translation (NMT), simultaneous neural machine translation (SNMT), the task of translating in real time before a full sentence has been observed, remains challenging due to the syntactic structure difference and simultaneity requirements.
Fitness Done Right: a Real-time Intelligent Personal Trainer for Exercise Correction
Finally, key values for key features of the two poses are computed correspondingly in the pose error detection part, which helps give correction advice.
Controllable Data Synthesis Method for Grammatical Error Correction
We propose two data synthesis methods which can control the error rate and the ratio of error types on synthetic data.
Incorporating Sememes into Chinese Definition Modeling
To accomplish this task, we construct the Chinese Definition Modeling Corpus (CDM), which contains triples of word, sememes and the corresponding definition.
Meta-Learning for Low-Resource Neural Machine Translation
We frame low-resource translation as a meta-learning problem, and we learn to adapt to low-resource languages based on multilingual high-resource language tasks.
Low Resource Neural Machine Translation
Low-Resource Neural Machine Translation
+4
A Stable and Effective Learning Strategy for Trainable Greedy Decoding
Beam search is a widely used approximate search strategy for neural network decoders, and it generally outperforms simple greedy decoding on tasks like machine translation.
Zero-Resource Neural Machine Translation with Multi-Agent Communication Game
While end-to-end neural machine translation (NMT) has achieved notable success in the past years in translating a handful of resource-rich language pairs, it still suffers from the data scarcity problem for low-resource language pairs and domains.
A Teacher-Student Framework for Zero-Resource Neural Machine Translation
While end-to-end neural machine translation (NMT) has made remarkable progress recently, it still suffers from the data scarcity problem for low-resource language pairs and domains.
