Search Results for author:
Found 77 papers, 37 papers with code
Cross-composition Feature Disentanglement for Compositional Zero-shot Learning
Disentanglement of visual features of primitives (i. e., attributes and objects) has shown exceptional results in Compositional Zero-shot Learning (CZSL).
AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation
Moreover, to increase the difficulty diversity of generated planning tasks, we propose a bidirectional evolution method, Bi-Evol, that evolves planning tasks from easier and harder directions to synthesize a task set with a smoother difficulty curve.
Arena Learning: Build Data Flywheel for LLMs Post-training via Simulated Chatbot Arena
In this paper, we introduce Arena Learning, an innovative offline strategy designed to simulate these arena battles using AI-driven annotations to evaluate battle outcomes, thus facilitating the continuous improvement of the target model through both supervised fine-tuning and reinforcement learning.
Improving Graph Out-of-distribution Generalization on Real-world Data
In contrast to previous studies that impose rigid independence assumptions on environments and invariant sub-graphs, this paper presents the theorems of environment-label dependency and mutable rationale invariance, where the former characterizes the usefulness of environments in determining graph labels while the latter refers to the mutable importance of graph rationales.
Automatic Instruction Evolving for Large Language Models
Fine-tuning large pre-trained language models with Evol-Instruct has achieved encouraging results across a wide range of tasks.
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
We introduce phi-3-mini, a 3. 8 billion parameter language model trained on 3. 3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3. 5 (e. g., phi-3-mini achieves 69% on MMLU and 8. 38 on MT-bench), despite being small enough to be deployed on a phone.
Ranked #5 on
MMR total
on MRR-Benchmark
(using extra training data)
A Survey on Knowledge Distillation of Large Language Models
In the era of Large Language Models (LLMs), Knowledge Distillation (KD) emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their open-source counterparts like LLaMA and Mistral.
Diffusion-based Graph Generative Methods
Being the most cutting-edge generative methods, diffusion methods have shown great advances in wide generation tasks.
A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions
In this survey, we comprehensively review existing works on learning from graphs with heterophily.
Leveraging Large Language Models for NLG Evaluation: Advances and Challenges
In the rapidly evolving domain of Natural Language Generation (NLG) evaluation, introducing Large Language Models (LLMs) has opened new avenues for assessing generated content quality, e. g., coherence, creativity, and context relevance.
Geometric-Facilitated Denoising Diffusion Model for 3D Molecule Generation
The second challenge involves accommodating molecule generation to diffusion and accurately predicting the existence of bonds.
Multi-Attribute Interactions Matter for 3D Visual Grounding
3D visual grounding aims to localize 3D objects described by free-form language sentences.
WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning
Recent work demonstrates that, after instruction tuning, Code Large Language Models (Code LLMs) can obtain impressive capabilities to address a wide range of code-related tasks.
AirIMU: Learning Uncertainty Propagation for Inertial Odometry
In contrast, data-driven IO methods struggle to accurately model the sensor motions, often leading to generalizability and interoperability issues.
Re-Reading Improves Reasoning in Large Language Models
To enhance the reasoning capabilities of off-the-shelf Large Language Models (LLMs), we introduce a simple, yet general and effective prompting method, Re2, i. e., \textbf{Re}-\textbf{Re}ading the question as input.
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
Through extensive experiments on two mathematical reasoning benchmarks, namely GSM8k and MATH, we reveal the extraordinary capabilities of our model.
Ranked #51 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
Investigating the Learning Behaviour of In-context Learning: A Comparison with Supervised Learning
Large language models (LLMs) have shown remarkable capacity for in-context learning (ICL), where learning a new task from just a few training examples is done without being explicitly pre-trained.
WizardCoder: Empowering Code Large Language Models with Evol-Instruct
Moreover, our model even outperforms the largest closed LLMs, Anthropic's Claude and Google's Bard, on HumanEval and HumanEval+.
Ranked #4 on
Code Generation
on CodeContests
Synergistic Interplay between Search and Large Language Models for Information Retrieval
Information retrieval (IR) plays a crucial role in locating relevant resources from vast amounts of data, and its applications have evolved from traditional knowledge bases to modern retrieval models (RMs).
Augmented Large Language Models with Parametric Knowledge Guiding
We demonstrate that our PKG framework can enhance the performance of "black-box" LLMs on a range of domain knowledge-intensive tasks that require factual (+7. 9%), tabular (+11. 9%), medical (+3. 0%), and multimodal (+8. 1%) knowledge.
Self-Supervised Multi-Modal Sequential Recommendation
To address this issue, we propose a dual-tower retrieval architecture for sequence recommendation.
WizardLM: Empowering Large Language Models to Follow Complex Instructions
In this paper, we show an avenue for creating large amounts of instruction data with varying levels of complexity using LLM instead of humans.
LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Retrieval
The conventional dense retrieval paradigm relies on encoding images and texts into dense representations using dual-stream encoders, however, it faces challenges with low retrieval speed in large-scale retrieval scenarios.
LexLIP: Lexicon-Bottlenecked Language-Image Pre-Training for Large-Scale Image-Text Sparse Retrieval
To address this issue, we propose a novel sparse retrieval paradigm for ITR that exploits sparse representations in the vocabulary space for images and texts.
Iterative Proposal Refinement for Weakly-Supervised Video Grounding
Weakly-Supervised Video Grounding (WSVG) aims to localize events of interest in untrimmed videos with only video-level annotations.
Fine-Grained Distillation for Long Document Retrieval
Long document retrieval aims to fetch query-relevant documents from a large-scale collection, where knowledge distillation has become de facto to improve a retriever by mimicking a heterogeneous yet powerful cross-encoder.
Adam: Dense Retrieval Distillation with Adaptive Dark Examples
Different from previous works that only rely on one positive and hard negatives as candidate passages, we create dark examples that all have moderate relevance to the query through mixing-up and masking in discrete space.
Latent User Intent Modeling for Sequential Recommenders
We demonstrate the effectiveness of the latent user intent modeling via offline analyses as well as live experiments on a large-scale industrial recommendation platform.
MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation
First, it is the largest multi-modal conversation dataset by the number of dialogues by 88x.
Ranked #2 on
Multimodal Intent Recognition
on MMDialog
Reward Shaping for User Satisfaction in a REINFORCE Recommender
How might we design Reinforcement Learning (RL)-based recommenders that encourage aligning user trajectories with the underlying user satisfaction?
LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval
In large-scale retrieval, the lexicon-weighting paradigm, learning weighted sparse representations in vocabulary space, has shown promising results with high quality and low latency.
LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval
The alignment is achieved by weakened knowledge distillations to enlighten the retriever via two aspects -- 1) a lexicon-augmented contrastive objective to challenge the dense encoder and 2) a pair-wise rank-consistent regularization to make dense model's behavior incline to the other.
LFGCF: Light Folksonomy Graph Collaborative Filtering for Tag-Aware Recommendation
Recently, many efforts have been devoted to improving Tag-aware recommendation systems (TRS) with Graph Convolutional Networks (GCN), which has become new state-of-the-art for the general recommendation.
KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP
This paper focuses on the data augmentation for low-resource NLP tasks where the training set is limited.
Towards Robust Ranker for Text Retrieval
A ranker plays an indispensable role in the de facto 'retrieval & rerank' pipeline, but its training still lags behind -- learning from moderate negatives or/and serving as an auxiliary module for a retriever.
UnifieR: A Unified Retriever for Large-Scale Retrieval
Large-scale retrieval is to recall relevant documents from a huge collection given a query.
Stylized Knowledge-Grounded Dialogue Generation via Disentangled Template Rewriting
(2) How to cohere with context and preserve the knowledge when generating a stylized response.
TegTok: Augmenting Text Generation via Task-specific and Open-world Knowledge
To address the problem, we propose augmenting TExt Generation via Task-specific and Open-world Knowledge (TegTok) in a unified framework.
PromDA: Prompt-based Data Augmentation for Low-Resource NLU Tasks
This paper focuses on the Data Augmentation for low-resource Natural Language Understanding (NLU) tasks.
PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings
A straightforward solution is resorting to more diverse positives from a multi-augmenting strategy, while an open question remains about how to unsupervisedly learn from the diverse positives but with uneven augmenting qualities in the text field.
Recency Dropout for Recurrent Recommender Systems
Recurrent recommender systems have been successful in capturing the temporal dynamics in users' activity trajectories.
Small Changes Make Big Differences: Improving Multi-turn Response Selection in Dialogue Systems via Fine-Grained Contrastive Learning
The sequence representation plays a key role in the learning of matching degree between the dialogue context and the response.
Multimodal Dialogue Response Generation
In such a low-resource setting, we devise a novel conversational agent, Divter, in order to isolate parameters that depend on multimodal dialogues from the entire generation model.
RecInDial: A Unified Framework for Conversational Recommendation with Pretrained Language Models
Furthermore, we propose to evaluate the CRS models in an end-to-end manner, which can reflect the overall performance of the entire system rather than the performance of individual modules, compared to the separate evaluations of the two modules used in previous work.
Learning Neural Templates for Recommender Dialogue System
Second, only the items mentioned in the training corpus have a chance to be recommended in the conversation.
Contextual Fine-to-Coarse Distillation for Coarse-grained Response Selection in Open-Domain Conversations
We study the problem of coarse-grained response selection in retrieval-based dialogue systems.
Learning to Ground Visual Objects for Visual Dialog
Specifically, a posterior distribution over visual objects is inferred from both context (history and questions) and answers, and it ensures the appropriate grounding of visual objects during the training process.
Neural Rule-Execution Tracking Machine For Transformer-Based Text Generation
Sequence-to-Sequence (S2S) neural text generation models, especially the pre-trained ones (e. g., BART and T5), have exhibited compelling performance on various natural language generation tasks.
MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding
Recently, various neural models for multi-party conversation (MPC) have achieved impressive improvements on a variety of tasks such as addressee recognition, speaker identification and response prediction.
Maria: A Visual Experience Powered Conversational Agent
The retriever aims to retrieve a correlated image to the dialog from an image index, while the visual concept detector extracts rich visual knowledge from the image.
ProphetNet-X: Large-Scale Pre-training Models for English, Chinese, Multi-lingual, Dialog, and Code Generation
ProphetNet is a pre-training based natural language generation method which shows powerful performance on English text summarization and question generation tasks.
Learning Matching Representations for Individualized Organ Transplantation Allocation
Organ transplantation is often the last resort for treating end-stage illness, but the probability of a successful transplantation depends greatly on compatibility between donors and recipients.
Are Pre-trained Language Models Knowledgeable to Ground Open Domain Dialogues?
We study knowledge-grounded dialogue generation with pre-trained language models.
Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
We study knowledge-grounded dialogue generation with pre-trained language models.
StyleDGPT: Stylized Response Generation with Pre-trained Language Models
Generating responses following a desired style has great potentials to extend applications of open-domain dialogue systems, yet is refrained by lacking of parallel data for training.
Zero-Resource Knowledge-Grounded Dialogue Generation
While neural conversation models have shown great potentials towards generating informative and engaging responses via introducing external knowledge, learning such a model often requires knowledge-grounded dialogues that are difficult to obtain.
Open Domain Dialogue Generation with Latent Images
Thus, we propose learning a response generation model with both image-grounded dialogues and textual dialogues by assuming that the visual scene information at the time of a conversation can be represented by an image, and trying to recover the latent images of the textual dialogues through text-to-image generation techniques.
Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks
We study multi-turn response generation for open-domain dialogues.
Low-Resource Knowledge-Grounded Dialogue Generation
In such a low-resource setting, we devise a disentangled response decoder in order to isolate parameters that depend on knowledge-grounded dialogues from the entire generation model.
THUEE system description for NIST 2019 SRE CTS Challenge
This paper describes the systems submitted by the department of electronic engineering, institute of microelectronics of Tsinghua university and TsingMicro Co. Ltd. (THUEE) to the NIST 2019 speaker recognition evaluation CTS challenge.
Read, Attend and Comment: A Deep Architecture for Automatic NewsComment Generation
Automatic news comment generation is a new testbed for techniques of natural language generation.
Read, Attend and Comment: A Deep Architecture for Automatic News Comment Generation
Automatic news comment generation is a new testbed for techniques of natural language generation.
Low-Resource Response Generation with Template Prior
Since the paired data now is no longer enough to train a neural generation model, we consider leveraging the large scale of unpaired data that are much easier to obtain, and propose response generation with both paired and unpaired data.
One Time of Interaction May Not Be Enough: Go Deep with an Interaction-over-Interaction Network for Response Selection in Dialogues
Currently, researchers have paid great attention to retrieval-based dialogues in open-domain.
Ranked #12 on
Conversational Response Selection
on Douban
Neural Response Generation with Meta-Words
We present open domain response generation with meta-words.
A Document-grounded Matching Network for Response Selection in Retrieval-based Chatbots
We present a document-grounded matching network (DGMN) for response selection that can power a knowledge-aware retrieval-based chatbot system.
Towards Neural Mixture Recommender for Long Range Dependent User Sequences
Our approach employs a mixture of models, each with a different temporal range.
Multiobjective Optimization Training of PLDA for Speaker Verification
Most current state-of-the-art text-independent speaker verification systems take probabilistic linear discriminant analysis (PLDA) as their backend classifiers.
Multiobjective Optimization
Text-Independent Speaker Verification
Playing 20 Question Game with Policy-Based Reinforcement Learning
The 20 Questions (Q20) game is a well known game which encourages deductive reasoning and creativity.
Improving Matching Models with Hierarchical Contextualized Representations for Multi-turn Response Selection
In this paper, we study context-response matching with pre-trained contextualized representations for multi-turn response selection in retrieval-based chatbots.
Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts
We study open domain dialogue generation with dialogue acts designed to explain how people engage in social chat.
Towards Interpretable Chit-chat: Open Domain Dialogue Generation with Dialogue Acts
Conventional methods model open domain dialogue generation as a black box through end-to-end learning from large scale conversation data.
Neural Response Generation with Dynamic Vocabularies
We study response generation for open domain conversation in chatbots.
A Sequential Matching Framework for Multi-turn Response Selection in Retrieval-based Chatbots
The task requires matching a response candidate with a conversation context, whose challenges include how to recognize important parts of the context, and how to model the relationships among utterances in the context.
Large Margin Discriminant Dimensionality Reduction in Prediction Space
We argue that the intermediate mapping, e. g. boosting predictor, is preserving the discriminant aspects of the data and by controlling the dimension of this mapping it is possible to achieve discriminant low dimensional representations for the data.
Visual Sentiment Prediction with Deep Convolutional Neural Networks
Images have become one of the most popular types of media through which users convey their emotions within online social networks.
Learning Receptive Fields for Pooling from Tensors of Feature Response
A new method for learning pooling receptive fields for recognition is presented.
