Search Results for author:
Found 53 papers, 22 papers with code
Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
As a drop-in enhancement to the existing RLHF workflow, our causal reward modeling provides a practical way to improve the trustworthiness and fairness of LLM finetuning.
Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following
To address this gap, we introduce Multi-IF, a new benchmark designed to assess LLMs' proficiency in following multi-turn and multilingual instructions.
Preference Optimization with Multi-Sample Comparisons
However, current post-training methods such as reinforcement learning from human feedback (RLHF) and direct alignment from preference methods (DAP) primarily utilize single-sample comparisons.
Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning
In CORY, the LLM to be fine-tuned is initially duplicated into two autonomous agents: a pioneer and an observer.
The Perfect Blend: Redefining RLHF with Mixture of Judges
However, RLHF has limitations in multi-task learning (MTL) due to challenges of reward hacking and extreme multi-objective optimization (i. e., trade-off of multiple and/or sometimes conflicting objectives).
Language-Queried Target Sound Extraction Without Parallel Training Data
In a vanilla language-free training stage, target audio is encoded using the pre-trained CLAP audio encoder to form a condition embedding for the TSE model, while during inference, user language queries are encoded by CLAP text encoder.
ECAFormer: Low-light Image Enhancement using Cross Attention
Low-light image enhancement (LLIE) is critical in computer vision.
Stochastic Online Optimization for Cyber-Physical and Robotic Systems
We propose a novel gradient-based online optimization framework for solving stochastic programming problems that frequently arise in the context of cyber-physical and robotic systems.
PE-GPT: A Physics-Informed Interactive Large Language Model for Power Converter Modulation Design
This paper proposes PE-GPT, a custom-tailored large language model uniquely adapted for power converter modulation design.
CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction
Universal sound separation (USS) aims to extract arbitrary types of sounds from real-world recordings.
Ranked #1 on
Target Sound Extraction
on AudioSet
Poisoning Attacks against Recommender Systems: A Survey
This survey paper provides a systematic and up-to-date review of the research landscape on Poisoning Attacks against Recommendation (PAR).
Extending Whisper with prompt tuning to target-speaker ASR
Target-speaker automatic speech recognition (ASR) aims to transcribe the desired speech of a target speaker from multi-talker overlapped utterances.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Adversarial Driving Behavior Generation Incorporating Human Risk Cognition for Autonomous Vehicle Evaluation
Autonomous vehicle (AV) evaluation has been the subject of increased interest in recent years both in industry and in academia.
Effective Long-Context Scaling of Foundation Models
We also examine the impact of various design choices in the pretraining process, including the data mix and the training curriculum of sequence lengths -- our ablation experiments suggest that having abundant long texts in the pretrain dataset is not the key to achieving strong performance, and we empirically verify that long context continual pretraining is more efficient and similarly effective compared to pretraining from scratch with long sequences.
Black-Box vs. Gray-Box: A Case Study on Learning Table Tennis Ball Trajectory Prediction with Spin and Impacts
Our gray-box approach builds on a physical model.
Detection of brain activations induced by naturalistic stimuli in a pseudo model-driven way
We evaluated the effectiveness of AINS with both statistical and predictive analyses on individual differences in sex and intelligence quotient (IQ), based on the four movie fMRI runs included in the Human Connectome Project dataset.
A Tightly Coupled LiDAR-IMU Odometry through Iterated Point-Level Undistortion
Scan undistortion is a key module for LiDAR odometry in high dynamic environment with high rotation and translation speed.
IDPG: An Instance-Dependent Prompt Generation Method
Prompt tuning is a new, efficient NLP transfer learning paradigm that adds a task-specific prompt in each input instance during the model training stage.
Heat Conduction Plate Layout Optimization using Physics-driven Convolutional Neural Networks
The layout optimization of the heat conduction is essential during design in engineering, especially for thermal sensible products.
Reducing Target Group Bias in Hate Speech Detectors
The ubiquity of offensive and hateful content on online fora necessitates the need for automatic solutions that detect such content competently across target groups.
RID-Noise: Towards Robust Inverse Design under Noisy Environments
We also define a sample-wise weight, which can be used in the maximum weighted likelihood estimation of an inverse model based on a cINN.
Neural Image Beauty Predictor Based on Bradley-Terry Model
This work focuses on image beauty assessment.
UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning
Recent parameter-efficient language model tuning (PELT) methods manage to match the performance of fine-tuning with much fewer trainable parameters and perform especially well when training data is limited.
Luna: Linear Unified Nested Attention
Specifically, with the first attention function, Luna packs the input sequence into a sequence of fixed length.
Entailment as Few-Shot Learner
Large pre-trained language models (LMs) have demonstrated remarkable ability as few-shot learners.
Ranked #1 on
Topic Classification
on OS
On the Influence of Masking Policies in Intermediate Pre-training
Current NLP models are predominantly trained through a two-stage "pre-train then fine-tune" pipeline.
On Unifying Misinformation Detection
In this paper, we introduce UnifiedM2, a general-purpose misinformation model that jointly models multiple domains of misinformation with a single, unified setup.
Studying Strategically: Learning to Mask for Closed-book QA
Thus, our policy packs task-relevant knowledge into the parameters of a language model.
CLEAR: Contrastive Learning for Sentence Representation
Pre-trained language models have proven their unique powers in capturing implicit language features.
Ranked #5 on
Question Answering
on Quora Question Pairs
A Simple and Efficient Registration of 3D Point Cloud and Image Data for Indoor Mobile Mapping System
Registration of 3D LiDAR point clouds with optical images is critical in the combination of multi-source data.
A Method of Generating Measurable Panoramic Image for Indoor Mobile Measurement System
This paper designs a technique route to generate high-quality panoramic image with depth information, which involves two critical research hotspots: fusion of LiDAR and image data and image stitching.
A marine radioisotope gamma-ray spectrum analysis method based on Monte Carlo simulation and MLP neural network
We apply multilayer perceptron (MLP) to analyze the 662 keV full energy peak of Cs-137 in the seawater spectrum.
Preserving Integrity in Online Social Networks
Online social networks provide a platform for sharing information and free expression.
To Pretrain or Not to Pretrain: Examining the Benefits of Pretrainng on Resource Rich Tasks
Pretraining NLP models with variants of Masked Language Model (MLM) objectives has recently led to a significant improvements on many tasks.
To Pretrain or Not to Pretrain: Examining the Benefits of Pretraining on Resource Rich Tasks
Pretraining NLP models with variants of Masked Language Model (MLM) objectives has recently led to a significant improvements on many tasks.
Linformer: Self-Attention with Linear Complexity
Large transformer models have shown extraordinary success in achieving state-of-the-art results in many natural language processing applications.
Language Models as Fact Checkers?
Recent work has suggested that language models (LMs) store both common-sense and factual knowledge learned from pre-training data.
A Combined Data-driven and Physics-driven Method for Steady Heat Conduction Prediction using Deep Convolutional Neural Networks
For the data-driven based method, the introduction of physical equation not only is able to speed up the convergence, but also produces physically more consistent solutions.
CAE-LO: LiDAR Odometry Leveraging Fully Unsupervised Convolutional Auto-Encoder for Interest Point Detection and Feature Description
As an important technology in 3D mapping, autonomous driving, and robot navigation, LiDAR odometry is still a challenging task.
Blockwise Self-Attention for Long Document Understanding
We present BlockBERT, a lightweight and efficient BERT model for better modeling long-distance dependencies.
Exploring Deep Multimodal Fusion of Text and Photo for Hate Speech Classification
Interactions among users on social network platforms are usually positive, constructive and insightful.
NetSMF: Large-Scale Network Embedding as Sparse Matrix Factorization
Previous research shows that 1) popular network embedding benchmarks, such as DeepWalk, are in essence implicitly factorizing a matrix with a closed form, and 2)the explicit factorization of such matrix generates more powerful embeddings than existing methods.
DeepInf: Social Influence Prediction with Deep Learning
Inspired by the recent success of deep neural networks in a wide range of computing applications, we design an end-to-end framework, DeepInf, to learn users' latent feature representation for predicting social influence.
A Web-scale system for scientific knowledge exploration
To enable efficient exploration of Web-scale scientific knowledge, it is necessary to organize scientific publications into a hierarchical concept structure.
GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
We propose a new network architecture, Gated Attention Networks (GaAN), for learning on graphs.
Ranked #1 on
Node Property Prediction
on ogbn-proteins
Revisiting Knowledge Base Embedding as Tensor Decomposition
We study the problem of knowledge base (KB) embedding, which is usually addressed through two frameworks---neural KB embedding and tensor decomposition.
Network Embedding as Matrix Factorization: Unifying DeepWalk, LINE, PTE, and node2vec
This work lays the theoretical foundation for skip-gram based network embedding methods, leading to a better understanding of latent network representation learning.
A Neural Comprehensive Ranker (NCR) for Open-Domain Question Answering
This paper proposes a novel neural machine reading model for open-domain question answering at scale.
KeyVec: Key-semantics Preserving Document Representations
Previous studies have demonstrated the empirical success of word embeddings in various applications.
A Century of Science: Globalization of Scientific Collaborations, Citations, and Innovations
We find that science has benefited from the shift from individual work to collaborative effort, with over 90% of the world-leading innovations generated by collaborations in this century, nearly four times higher than they were in the 1900s.
Digital Libraries Social and Information Networks Physics and Society
An Overview of Microsoft Academic Service (MAS) and Applications
In addition to obtaining these entities from the publisher feeds as in the previous effort, we in this version include data mining results from the Web index and an in-house knowledge base from Bing, a major commercial search engine.
An experimental study on implicit social recommendation
In this paper, we study the following two research problems: (1) In some systems without explicit social information, can we still improve recommender systems using implicit social information?
