Search Results for author:
Found 25 papers, 7 papers with code
MTL-SLT: Multi-Task Learning for Spoken Language Tasks
The proposed framework benefits from three key aspects: 1) pre-trained sub-networks of ASR model and language model; 2) multi-task learning objective to exploit shared knowledge from different tasks; 3) end-to-end training of ASR and downstream NLP task based on sequence loss.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning
Vision-Language Models (VLMs) excel in many direct multimodal tasks but struggle to translate this prowess into effective decision-making within interactive, visually rich environments like games.
Kimi-VL Technical Report
We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong agent capabilities - all while activating only 2. 8B parameters in its language decoder (Kimi-VL-A3B).
Efficient Inference for Large Reasoning Models: A Survey
Large Reasoning Models (LRMs) significantly improve the reasoning ability of Large Language Models (LLMs) by learning to reason, exhibiting promising performance in complex task-solving.
CountLLM: Towards Generalizable Repetitive Action Counting via Large Language Model
To address these challenges, we propose CountLLM, the first large language model (LLM)-based framework that takes video data and periodic text prompts as inputs and outputs the desired counting value.
A Survey of Model Architectures in Information Retrieval
This survey examines the evolution of model architectures in information retrieval (IR), focusing on two key aspects: backbone models for feature extraction and end-to-end system architectures for relevance estimation.
MoBA: Mixture of Block Attention for Long-Context LLMs
Scaling the effective context length is essential for advancing large language models (LLMs) toward artificial general intelligence (AGI).
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Moreover, we present effective long2short methods that use long-CoT techniques to improve short-CoT models, yielding state-of-the-art short-CoT reasoning results -- e. g., 60. 8 on AIME, 94. 6 on MATH500, 47. 3 on LiveCodeBench -- outperforming existing short-CoT models such as GPT-4o and Claude Sonnet 3. 5 by a large margin (up to +550%).
FD2Talk: Towards Generalized Talking Head Generation with Facial Decoupled Diffusion Model
Therefore, we propose a Facial Decoupled Diffusion model for Talking head generation called FD2Talk, which fully leverages the advantages of diffusion models and decouples the complex facial details through multi-stages.
Knowledge-enhanced Prompt Tuning for Dialogue-based Relation Extraction with Trigger and Label Semantic
Specifically, we propose two beneficial tasks, masked trigger prediction, and verbalizer representation learning, to effectively inject trigger knowledge and label semantic knowledge respectively.
Mask-ControlNet: Higher-Quality Image Generation with An Additional Mask Prompt
Then, the object images are employed as additional prompts to facilitate the diffusion model to better understand the relationship between foreground and background regions during image generation.
Are Large Language Models Really Robust to Word-Level Perturbations?
Notably, we are surprised to discover that robustness tends to decrease as fine-tuning (SFT and RLHF) is conducted.
Soft Prompt Decoding for Multilingual Dense Retrieval
In this work, we explore a Multilingual Information Retrieval (MLIR) task, where the collection includes documents in multiple languages.
Cross-Lingual Information Retrieval
Knowledge Distillation
+1
Cross-lingual Knowledge Transfer via Distillation for Multilingual Information Retrieval
In this paper, we introduce the approach behind our submission for the MIRACL challenge, a WSDM 2023 Cup competition that centers on ad-hoc retrieval across 18 diverse languages.
Improving Cross-lingual Information Retrieval on Low-Resource Languages via Optimal Transport Distillation
Moreover, unlike the English-to-English retrieval task, where large-scale training collections for document ranking such as MS MARCO are available, the lack of cross-lingual retrieval data for low-resource language makes it more challenging for training cross-lingual retrieval models.
Towards Joint Intent Detection and Slot Filling via Higher-order Attention
Intent detection (ID) and Slot filling (SF) are two major tasks in spoken language understanding (SLU).
Mixed Attention Transformer for Leveraging Word-Level Knowledge to Neural Cross-Lingual Information Retrieval
In the monolingual retrieval task, because of the same lexical inputs, it is easier for model to identify the query terms that occurred in documents.
HAN: Higher-order Attention Network for Spoken Language Understanding
Spoken Language Understanding (SLU), including intent detection and slot filling, is a core component in human-computer interaction.
GhostBERT: Generate More Features with Cheap Operations for BERT
Transformer-based pre-trained language models like BERT, though powerful in many tasks, are expensive in both memory and computation, due to their large number of parameters.
Audio-Oriented Multimodal Machine Comprehension: Task, Dataset and Model
As a result, the proposed approach can handle various tasks including: Audio-Oriented Multimodal Machine Comprehension, Machine Reading Comprehension and Machine Listening Comprehension, in a single model, making fair comparisons possible between our model and the existing unimodal MC models.
Federated Learning for Spoken Language Understanding
To this end, we propose a federated learning framework, which could unify various types of datasets as well as tasks to learn and fuse various types of knowledge, i. e., text representations, from different datasets and tasks, without the sharing of downstream task data.
PIN: A Novel Parallel Interactive Network for Spoken Language Understanding
However, we noted that, so far, the efforts to obtain better performance by supporting bidirectional and explicit information exchange between ID and SF are not well studied. In addition, few studies attempt to capture the local context information to enhance the performance of SF.
DynaBERT: Dynamic BERT with Adaptive Width and Depth
The pre-trained language models like BERT, though powerful in many natural language processing tasks, are both computation and memory expensive.
The Simons Observatory: Science goals and forecasts
With up to an order of magnitude lower polarization noise than maps from the Planck satellite, the high-resolution sky maps will constrain cosmological parameters derived from the damping tail, gravitational lensing of the microwave background, the primordial bispectrum, and the thermal and kinematic Sunyaev-Zel'dovich effects, and will aid in delensing the large-angle polarization signal to measure the tensor-to-scalar ratio.
Cosmology and Nongalactic Astrophysics
The CMB bispectrum from recombination
We compute the cosmic microwave background temperature bispectrum generated by nonlinearities at recombination on all scales.
Cosmology and Nongalactic Astrophysics General Relativity and Quantum Cosmology High Energy Physics - Phenomenology High Energy Physics - Theory 83F05 J.2
