Search Results for author:
Found 88 papers, 49 papers with code
Preserving Cross-Linguality of Pre-trained Models via Continual Learning
Recently, fine-tuning pre-trained language models (e. g., multilingual BERT) to downstream cross-lingual tasks has shown promising results.
CAiRE in DialDoc21: Data Augmentation for Information Seeking Dialogue System
Information-seeking dialogue systems, including knowledge identification and response generation, aim to respond to users with fluent, coherent, and informative responses based on users’ needs, which.
Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for advancing the reasoning capabilities of Large Language Models (LLMs).
AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy
Both approaches yield notable improvements in reasoning performance, with scaling the number of prompts resulting in more substantial gains.
Astraea: A GPU-Oriented Token-wise Acceleration Framework for Video Diffusion Transformers
To determine optimal token reduction for different timesteps, we further design a search framework that leverages a classic evolutionary algorithm to automatically determine the distribution of the token budget effectively.
Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models
Despite the remarkable reasoning performance, eliciting the long chain-of-thought (CoT) ability in large language models (LLMs) typically requires costly reinforcement learning or supervised fine-tuning on high-quality distilled data.
AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
Notably, we find that math-only RL not only significantly enhances the performance of strong distilled models on math benchmarks (e. g., +14. 6% / +17. 2% on AIME 2025 for the 7B / 14B models), but also code reasoning tasks (e. g., +6. 8% / +5. 8% on LiveCodeBench for the 7B / 14B models).
From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models
Long-context capabilities are essential for a wide range of applications, including document and video understanding, in-context learning, and inference-time scaling, all of which require models to process and reason over long sequences of text and multimodal data.
SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation
Text-to-song generation, the task of creating vocals and accompaniment from textual inputs, poses significant challenges due to domain complexity and data scarcity.
Hybrid Adaptive Modeling using Neural Networks Trained with Nonlinear Dynamics Based Features
The goal is to create a hybrid adaptive modeling framework that integrates data-based modeling with newly measured data and analytical nonlinear dynamical models for enhanced accuracy, parametric dependence, and improved generalizability.
AceMath: Advancing Frontier Math Reasoning with Post-Training and Reward Modeling
In this paper, we introduce AceMath, a suite of frontier math models that excel in solving complex math problems, along with highly effective reward models capable of evaluating generated solutions and reliably identifying the correct ones.
NVLM: Open Frontier-Class Multimodal LLMs
We introduce NVLM 1. 0, a family of frontier-class multimodal large language models (LLMs) that achieve state-of-the-art results on vision-language tasks, rivaling the leading proprietary models (e. g., GPT-4o) and open-access models (e. g., Llama 3-V 405B and InternVL 2).
vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving
This study introduces the vTensor, an innovative tensor structure for LLM inference based on GPU virtual memory management (VMM).
ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities
In this work, we introduce ChatQA 2, an Llama 3. 0-based model with a 128K context window, designed to bridge the gap between open-source LLMs and leading proprietary models (e. g., GPT-4-Turbo) in long-context understanding and retrieval-augmented generation (RAG) capabilities.
RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs
Large language models (LLMs) typically utilize the top-k contexts from a retriever in retrieval-augmented generation (RAG).
Ranked #3 on
Question Answering
on PubMedQA
Nemotron-4 340B Technical Report
We release the Nemotron-4 340B model family, including Nemotron-4-340B-Base, Nemotron-4-340B-Instruct, and Nemotron-4-340B-Reward.
Astrocytic NMDA Receptors Modulate the Dynamics of Continuous Attractors
Our results show that blocking astrocytic NMDA receptors stabilizes attractor states and diminishes their mobility.
Multi-Behavior Generative Recommendation
We formulate the MBSR task into a consecutive two-step process: (1) given item sequences, MBGen first predicts the next behavior type to frame the user intention, (2) given item sequences and a target behavior type, MBGen then predicts the next items.
Mixture of Low-rank Experts for Transferable AI-Generated Image Detection
Remarkably, our best-performing ViT-L/14 variant requires training only 0. 08% of its parameters to surpass the leading baseline by +3. 64% mAP and +12. 72% avg. Acc across unseen diffusion and autoregressive models.
SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition
Creating lyrics and melodies for the vocal track in a symbolic format, known as song composition, demands expert musical knowledge of melody, an advanced understanding of lyrics, and precise alignment between them.
Understanding Public Perceptions of AI Conversational Agents: A Cross-Cultural Analysis
We find Chinese participants tended to view CAs hedonically, perceived voice-based and physically embodied CAs as warmer and more competent, and generally expressed positive emotions.
FGBERT: Function-Driven Pre-trained Gene Language Model for Metagenomics
Metagenomic data, comprising mixed multi-species genomes, are prevalent in diverse environments like oceans and soils, significantly impacting human health and ecological functions.
ChatQA: Surpassing GPT-4 on Conversational QA and RAG
In this work, we introduce ChatQA, a suite of models that outperform GPT-4 on retrieval-augmented generation (RAG) and conversational question answering (QA).
Ranked #6 on
Question Answering
on TriviaQA
(using extra training data)
SUT: Active Defects Probing for Transcompiler Models
In this paper we introduce a new metrics for programming language translation and these metrics address these basic syntax errors.
Protein 3D Graph Structure Learning for Robust Structure-based Protein Property Prediction
To study this problem, we identify a Protein 3D Graph Structure Learning Problem for Robust Protein Property Prediction (PGSL-RP3), collect benchmark datasets, and present a protein Structure embedding Alignment Optimization framework (SAO) to mitigate the problem of structure embedding bias between the predicted and experimental protein structures.
Retrieval meets Long Context Large Language Models
Perhaps surprisingly, we find that LLM with 4K context window using simple retrieval-augmentation at generation can achieve comparable performance to finetuned LLM with 16K context window via positional interpolation on long context tasks, while taking much less computation.
Co-modeling the Sequential and Graphical Routes for Peptide Representation Learning
Peptides are formed by the dehydration condensation of multiple amino acids.
Only 5\% Attention Is All You Need: Efficient Long-range Document-level Neural Machine Translation
Document-level Neural Machine Translation (DocNMT) has been proven crucial for handling discourse phenomena by introducing document-level context information.
Efficient Prediction of Peptide Self-assembly through Sequential and Graphical Encoding
In recent years, there has been an explosion of research on the application of deep learning to the prediction of various peptide properties, due to the significant development and market potential of peptides.
Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition
In this work, we analyze the transferability of emotion recognition across three different languages--English, Mandarin Chinese, and Cantonese; and 2 different age groups--adults and the elderly.
AdaptGear: Accelerating GNN Training via Adaptive Subgraph-Level Kernels on GPUs
Graph neural networks (GNNs) are powerful tools for exploring and learning from graph structures and features.
Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study
Thus, it is still an open question: shall we pretrain large autoregressive LMs with retrieval?
Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient Debias
It has become cognitive inertia to employ cross-entropy loss function in classification related tasks.
Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning
Augmenting pretrained language models (LMs) with a vision encoder (e. g., Flamingo) has obtained the state-of-the-art results in image-to-text generation.
Improving (Dis)agreement Detection with Inductive Social Relation Information From Comment-Reply Interactions
(Dis)agreement detection aims to identify the authors' attitudes or positions (\textit{{agree, disagree, neutral}}) towards a specific text.
RHO ($ρ$): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding
Dialogue systems can leverage large pre-trained language models and knowledge to generate fluent and informative responses.
Cross-Domain Local Characteristic Enhanced Deepfake Video Detection
As ultra-realistic face forgery techniques emerge, deepfake detection has attracted increasing attention due to security concerns.
Plausible May Not Be Faithful: Probing Object Hallucination in Vision-Language Pre-training
Large-scale vision-language pre-trained (VLP) models are prone to hallucinate non-existent visual objects when generating text based on visual information.
ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization
In this work, we propose a fixed-length adaptive numerical data type called ANT to achieve low-bit quantization with tiny hardware overheads.
What Does the Gradient Tell When Attacking the Graph Structure
To address this issue, we propose a novel surrogate model with multi-level propagation that preserves the node dissimilarity information.
Effective Transfer Learning for Low-Resource Natural Language Understanding
Third, we propose to leverage different levels of domain-related corpora and additional masking of data in the pre-training for the cross-domain adaptation, and discover that more challenging pre-training can better address the domain discrepancy issue in the task knowledge transfer.
Exploiting Sentiment and Common Sense for Zero-shot Stance Detection
Meanwhile, ablation studies prove the significance of each module in our model.
Mere Contrastive Learning for Cross-Domain Sentiment Analysis
Cross-domain sentiment analysis aims to predict the sentiment of texts in the target domain using the model trained on the source domain to cope with the scarcity of labeled data.
Are Gradients on Graph Structure Reliable in Gray-box Attacks?
These errors arise from rough gradient usage due to the discreteness of the graph structure and from the unreliability in the meta-gradient on the graph structure.
Learning the Evolutionary and Multi-scale Graph Structure for Multivariate Time Series Forecasting
To equip the graph neural network with a flexible and practical graph structure, in this paper, we investigate how to model the evolutionary and multi-scale interactions of time series.
Graph Neural Network
Multivariate Time Series Forecasting
+2
SNP2Vec: Scalable Self-Supervised Pre-Training for Genome-Wide Association Study
We apply SNP2Vec to perform long-sequence genomics modeling, and we evaluate the effectiveness of our approach on predicting Alzheimer's disease risk in a Chinese cohort.
Multi-Stage Prompting for Knowledgeable Dialogue Generation
We propose a multi-stage prompting approach to generate knowledgeable responses from a single pretrained LM.
ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation
ASCEND (A Spontaneous Chinese-English Dataset) is a high-quality Mandarin Chinese-English code-switching corpus built on spontaneous multi-turn conversational dialogue sources collected in Hong Kong.
NER-BERT: A Pre-trained Model for Low-Resource Entity Tagging
Named entity recognition (NER) models generally perform poorly when large training datasets are unavailable for low-resource domains.
Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
Accordingly, we propose $\eta$-balanced mixup loss for complementary learning of the two sub-objectives.
Ranked #7 on
Image Classification
on Places205
Surrogate Representation Learning with Isometric Mapping for Gray-box Graph Adversarial Attacks
Gray-box graph attacks aim at disrupting the performance of the victim model by using inconspicuous attacks with limited knowledge of the victim model.
Powering Comparative Classification with Sentiment Analysis via Domain Adaptive Knowledge Transfer
We study Comparative Preference Classification (CPC) which aims at predicting whether a preference comparison exists between two entities in a given sentence and, if so, which entity is preferred over the other.
Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization
Multimodal abstractive summarization (MAS) models that summarize videos (vision modality) and their corresponding transcripts (text modality) are able to extract the essential information from massive multimodal data on the Internet.
X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing
Experimental results illustrate that our model can significantly outperform existing strong baselines in cross-lingual and cross-domain settings, and our model can also achieve a good generalization ability on target languages of target domains.
CAiRE in DialDoc21: Data Augmentation for Information-Seeking Dialogue System
Information-seeking dialogue systems, including knowledge identification and response generation, aim to respond to users with fluent, coherent, and informative responses based on users' needs, which.
Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters
This paper proposes KnowExpert, a framework to bypass the explicit retrieval process and inject knowledge into the pre-trained language models with lightweight adapters and adapt to the knowledge-grounded dialogue task.
Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translation
The data scarcity in low-resource languages has become a bottleneck to building robust neural machine translation systems.
Low Resource Neural Machine Translation
Low-Resource Neural Machine Translation
+2
AutoMix: Unveiling the Power of Mixup for Stronger Classifiers
Specifically, AutoMix reformulates the mixup classification into two sub-tasks (i. e., mixed sample generation and mixup classification) with corresponding sub-networks and solves them in a bi-level optimization framework.
Ranked #8 on
Image Classification
on Places205
Are Multilingual Models Effective in Code-Switching?
Multilingual language models have shown decent performance in multilingual and cross-lingual natural language understanding tasks.
AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization
State-of-the-art abstractive summarization models generally rely on extensive labeled data, which lowers their generalization ability on domains where such data are not available.
Multimodal End-to-End Sparse Model for Emotion Recognition
Existing works on multimodal affective computing tasks, such as emotion recognition, generally adopt a two-phase pipeline, first extracting feature representations for each single modality with hand-crafted algorithms and then performing end-to-end learning with the extracted features.
CrossNER: Evaluating Cross-Domain Named Entity Recognition
Cross-domain named entity recognition (NER) models are able to cope with the scarcity issue of NER samples in target domains.
Kungfupanda at SemEval-2020 Task 12: BERT-Based Multi-TaskLearning for Offensive Language Detection
Nowadays, offensive content in social media has become a serious problem, and automatically detecting offensive language is an essential task.
Cross-lingual Spoken Language Understanding with Regularized Representation Alignment
Despite the promising results of current cross-lingual models for spoken language understanding systems, they still suffer from imperfect cross-lingual representation alignments between the source and target languages, which makes the performance sub-optimal.
Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems
In this paper, we propose a method to embed the KB, of any size, directly into the model parameters.
Modality-Transferable Emotion Embeddings for Low-Resource Multimodal Emotion Recognition
Despite the recent achievements made in the multi-modal emotion recognition task, two problems still exist and have not been well investigated: 1) the relationship between different emotion categories are not utilized, which leads to sub-optimal performance; and 2) current models fail to cope well with low-resource emotions, especially for unseen emotions.
EmoGraph: Capturing Emotion Correlations using Graph Networks
Most emotion recognition methods tackle the emotion understanding task by considering individual emotion independently while ignoring their fuzziness nature and the interconnections among them.
Ranked #3 on
Emotion Classification
on SemEval 2018 Task 1E-c
Language Models as Few-Shot Learner for Task-Oriented Dialogue Systems
In this paper, we evaluate the priming few-shot ability of language models in the NLU, DST, DP and NLG tasks.
Meta-Transfer Learning for Code-Switched Speech Recognition
An increasing number of people in the world today speak a mixed-language as a result of being multilingual.
Exploring Fine-tuning Techniques for Pre-trained Cross-lingual Models via Continual Learning
Recently, fine-tuning pre-trained language models (e. g., multilingual BERT) to downstream cross-lingual tasks has shown promising results.
Kungfupanda at SemEval-2020 Task 12: BERT-Based Multi-Task Learning for Offensive Language Detection
Nowadays, offensive content in social media has become a serious problem, and automatically detecting offensive language is an essential task.
Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling
In this paper, we propose a Coarse-to-fine approach (Coach) for cross-domain slot filling.
Cross-Domain Named Entity Recognition
named-entity-recognition
+3
Variational Transformers for Diverse Response Generation
Despite the great promise of Transformers in many sequence modeling tasks (e. g., machine translation), their deterministic nature hinders them from generalizing to high entropy tasks such as dialogue response generation.
XPersona: Evaluating Multilingual Personalized Chatbot
Experimental results show that the multilingual trained models outperform the translation-pipeline and that they are on par with the monolingual models, with the advantage of having a single model across multiple languages.
Learning Fast Adaptation on Cross-Accented Speech Recognition
The great variability and complex characteristics of accents creates a major challenge for training a robust and accent-agnostic automatic speech recognition (ASR) system.
Audio and Speech Processing Sound
Zero-Resource Cross-Domain Named Entity Recognition
Existing models for cross-domain named entity recognition (NER) rely on numerous unlabeled corpus or labeled NER training data in target domains.
Ranked #1 on
Cross-Domain Named Entity Recognition
on CoNLL04
On the Importance of Word Order Information in Cross-lingual Sequence Labeling
To verify this hypothesis, we investigate whether making models insensitive to the word order of the source language can improve the adaptation performance in target languages.
Universal Adversarial Perturbations for CNN Classifiers in EEG-Based BCIs
Multiple convolutional neural network (CNN) classifiers have been proposed for electroencephalogram (EEG) based brain-computer interfaces (BCIs).
Attention-Informed Mixed-Language Training for Zero-shot Cross-lingual Task-oriented Dialogue Systems
Recently, data-driven task-oriented dialogue systems have achieved promising performance in English.
Zero-shot Cross-lingual Dialogue Systems with Transferable Latent Variables
Despite the surging demands for multilingual task-oriented dialog systems (e. g., Alexa, Google Home), there has been less research done in multilingual or cross-lingual scenarios.
Generalizing Question Answering System with Pre-trained Language Model Fine-tuning
With a large number of datasets being released and new techniques being proposed, Question answering (QA) systems have witnessed great breakthroughs in reading comprehension (RC)tasks.
Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank Transformer
Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices.
Hierarchical Meta-Embeddings for Code-Switching Named Entity Recognition
In countries that speak multiple main languages, mixing up different languages within a conversation is commonly called code-switching.
Multi-Task Deep Learning with Dynamic Programming for Embryo Early Development Stage Classification from Time-Lapse Videos
Accurate classification of embryo early development stages can provide embryologists valuable information for assessing the embryo quality, and hence is critical to the success of IVF.
Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring
This paper describes CAiRE's submission to the unsupervised machine translation track of the WMT'19 news shared task from German to Czech.
CAiRE: An Empathetic Neural Chatbot
In this paper, we present an end-to-end empathetic conversation agent CAiRE.
Team yeon-zi at SemEval-2019 Task 4: Hyperpartisan News Detection by De-noising Weakly-labeled Data
This paper describes our system that has been submitted to SemEval-2019 Task 4: Hyperpartisan News Detection.
