Search Results for author:
Found 29 papers, 15 papers with code
Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence
We present Eagle (RWKV-5) and Finch (RWKV-6), sequence models improving upon the RWKV (RWKV-4) architecture.
Deep Prompt Multi-task Network for Abuse Language Detection
To address the problem, we propose a novel Deep Prompt Multi-task Network (DPMN) for abuse language detection.
StarCoder 2 and The Stack v2: The Next Generation
Our large model, StarCoder2- 15B, significantly outperforms other models of comparable size.
Ranked #25 on
Code Generation
on MBPP
Incorporating Exemplar Optimization into Training with Dual Networks for Human Mesh Recovery
(2) We devise a dual-network architecture to convey the novel training paradigm, which is composed of a main regression network and an auxiliary network, in which we can formulate the exemplar optimization loss function in the same form as the training loss function.
Adaptive Confidence Multi-View Hashing for Multimedia Retrieval
Furthermore, an adaptive confidence multi-view network is employed to measure the confidence of each view and then fuse multi-view features through a weighted summation.
The taste of IPA: Towards open-vocabulary keyword spotting and forced alignment in any language
In this project, we demonstrate that phoneme-based models for speech processing can achieve strong crosslinguistic generalizability to unseen languages.
Central Similarity Multi-View Hashing for Multimedia Retrieval
Hash representation learning of multi-view heterogeneous data is the key to improving the accuracy of multimedia retrieval.
CLIP Multi-modal Hashing: A new baseline CLIPMH
In this way, it can greatly improve the retrieval performance of multi-modal hashing methods.
Confidence Ranking for CTR Prediction
Model evolution and constant availability of data are two common phenomena in large-scale real-world machine learning applications, e. g. ads and recommendation systems.
RWKV: Reinventing RNNs for the Transformer Era
This work presents a significant step towards reconciling trade-offs between computational efficiency and model performance in sequence processing tasks.
Ranked #22 on
Natural Language Inference
on WNLI
StarCoder: may the source be with you!
The BigCode community, an open-scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder and StarCoderBase: 15. 5B parameter models with 8K context length, infilling capabilities and fast large-batch inference enabled by multi-query attention.
Ranked #43 on
Code Generation
on MBPP
Deep Metric Multi-View Hashing for Multimedia Retrieval
However, existing methods fail to effectively fuse the multi-view features and utilize the metric information provided by the dissimilar samples, leading to limited retrieval precision.
Dialogue-Contextualized Re-ranking for Medical History-Taking
We find that relative to the expert system, the best performance is achieved by our proposed global re-ranker with a transformer backbone, resulting in a 30% higher normalized discount cumulative gain (nDCG) and a 77% higher mean average precision (mAP).
The BigScience ROOTS Corpus: A 1.6TB Composite Multilingual Dataset
As language models grow ever larger, the need for large-scale high-quality text datasets has never been more pressing, especially in multilingual settings.
Multi-modal Large Language Model Enhanced Pseudo 3D Perception Framework for Visual Commonsense Reasoning
On the other hand, BLIP-2 as an MLLM is employed to process images and texts, and the referring expressions in texts involving specific visual objects are modified with linguistic object labels to serve as comprehensible MLLM inputs.
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions.
Bootstrapping meaning through listening: Unsupervised learning of spoken sentence embeddings
Inducing semantic representations directly from speech signals is a highly challenging task but has many useful applications in speech mining and spoken language understanding.
ByT5 model for massively multilingual grapheme-to-phoneme conversion
In this study, we tackle massively multilingual grapheme-to-phoneme conversion through implementing G2P models based on ByT5.
Rethinking Position Bias Modeling with Knowledge Distillation for CTR Prediction
Click-through rate (CTR) Prediction is of great importance in real-world online ads systems.
Dynamic Parameterized Network for CTR Prediction
Learning to capture feature relations effectively and efficiently is essential in click-through rate (CTR) prediction of modern recommendation systems.
Phone-to-audio alignment without text: A Semi-supervised Approach
The task of phone-to-audio alignment has many applications in speech research.
Idiosyncratic but not Arbitrary: Learning Idiolects in Online Registers Reveals Distinctive yet Consistent Individual Styles
Furthermore, we provide a description of idiolects through measuring inter- and intra-author variation, showing that variation in idiolects is often distinctive yet consistent.
Synchronising speech segments with musical beats in Mandarin and English singing
Generating synthesised singing voice with models trained on speech data has many advantages due to the models' flexibility and controllability.
The structure of online social networks modulates the rate of lexical change
Using Poisson regression and survival analysis, our study demonstrates that the community's network structure plays a significant role in lexical change.
Geodesic Paths for Image Segmentation with Implicit Region-based Homogeneity Enhancement
Minimal paths are regarded as a powerful and efficient tool for boundary detection and image segmentation due to its global optimality and the well-established numerical solutions such as fast marching method.
Probing the phonetic and phonological knowledge of tones in Mandarin TTS models
This study probes the phonetic and phonological knowledge of lexical tones in TTS models through two experiments.
A CNN-based tool for automatic tongue contour tracking in ultrasound images
This public available segmentation tool shows considerable promise for the automated tongue contour annotation of ultrasound images in speech research.
UM-IU@LING at SemEval-2019 Task 6: Identifying Offensive Tweets Using BERT and SVMs
This paper describes the UM-IU@LING's system for the SemEval 2019 Task 6: OffensEval.
Predicting tongue motion in unlabeled ultrasound videos using convolutional LSTM neural network
A challenge in speech production research is to predict future tongue movements based on a short period of past tongue movements.
