Search Results for author:
Found 45 papers, 20 papers with code
MAGI-1: Autoregressive Video Generation at Scale
We present MAGI-1, a world model that generates videos by autoregressively predicting a sequence of video chunks, defined as fixed-length segments of consecutive frames.
Walking the Tightrope: Disentangling Beneficial and Detrimental Drifts in Non-Stationary Custom-Tuning
This paper uncovers a critical yet overlooked phenomenon in multi-modal large language models (MLLMs): detrimental concept drift within chain-of-thought (CoT) reasoning during non-stationary reinforcement fine-tuning (RFT), where reasoning token distributions evolve unpredictably, thereby introducing significant biases in final predictions.
Learning Robust Spectral Dynamics for Temporal Domain Generalization
Modern machine learning models struggle to maintain performance in dynamic environments where temporal distribution shifts, \emph{i. e., concept drift}, are prevalent.
Who You Are Matters: Bridging Topics and Social Roles via LLM-Enhanced Logical Recommendation
Recommender systems filter contents/items valuable to users by inferring preferences from user features and historical behaviors.
Comprehensive List Generation for Multi-Generator Reranking
Reranking models solve the final recommendation lists that best fulfill users' demands.
Explicit Uncertainty Modeling for Video Watch Time Prediction
To improve the prediction accuracy for such an uncertain behavior, existing approaches show that one can either reduce the noise through duration bias modeling or formulate a distribution modeling task to capture the uncertainty.
LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation
To fill this gap, we propose LexRAG, the first benchmark to evaluate RAG systems for multi-turn legal consultations.
Rolling with the Punches: Resilient Contrastive Pre-training under Non-Stationary Drift
A critical emerging challenge is the effective pre-training of models on dynamic data streams characterized by concept drift, unpredictable changes in the underlying data distribution.
AI-driven Wireless Positioning: Fundamentals, Standards, State-of-the-art, and Challenges
Based on the AI/ML-assisted positioning and direct AI/ML positioning schemes outlined in the standards, we conduct an in-depth investigation of related research.
SALMONN-omni: A Codec-free LLM for Full-duplex Speech Understanding and Generation
Unlike traditional modularised conversational AI systems, which separate speech recognition, understanding, and text-to-speech generation into distinct components, multimodal LLMs operate as single end-to-end models.
k2SSL: A Faster and Better Framework for Self-Supervised Speech Representation Learning
Self-supervised learning (SSL) has achieved great success in speech-related tasks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Masked Image Contrastive Learning for Efficient Visual Conceptual Pre-training
This paper proposes a scalable and straightforward pre-training paradigm for efficient visual conceptual representation called masked image contrastive learning (MiCL).
CR-CTC: Consistency regularization on CTC for improved speech recognition
Connectionist Temporal Classification (CTC) is a widely used method for automatic speech recognition (ASR), renowned for its simplicity and computational efficiency.
Ranked #1 on
Speech Recognition
on GigaSpeech TEST
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
MT2KD: Towards A General-Purpose Encoder for Speech, Speaker, and Audio Events
In this work, MT2KD, a novel two-stage multi-task learning framework is proposed to build a general-purpose speech and audio encoder that jointly performs three fundamental tasks: automatic speech recognition (ASR), audio tagging (AT) and speaker verification (SV).
LibriheavyMix: A 20,000-Hour Dataset for Single-Channel Reverberant Multi-Talker Speech Separation, ASR and Speaker Diarization
This paper presents a large-scale far-field overlapping speech dataset, crafted to advance research in speech separation, recognition, and speaker diarization.
Interference Management in MIMO-ISAC Systems: A Transceiver Design Approach
The integrated sensing and communication (ISAC) system under multi-input multi-output (MIMO) architecture achieves dual functionalities of sensing and communication on the same platform by utilizing spatial gain, which provides a feasible paradigm facing spectrum congestion.
SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM
In inference, it boosts speeds by up to 37% and reduces memory by 1GB per GPU.
Adapting Multi-modal Large Language Model to Concept Drift From Pre-training Onwards
This mainly includes gradual drift due to long-tailed data and sudden drift from Out-Of-Distribution (OOD) data, both of which have increasingly drawn the attention of the research community.
Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language Models
Furthermore, we contribute a VG dataset, especially with multi-tasks.
Zipformer: A faster and better encoder for automatic speech recognition
The Conformer has become the most popular encoder model for automatic speech recognition (ASR).
Ranked #3 on
Speech Recognition
on WenetSpeech
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context
In this paper, we introduce Libriheavy, a large-scale ASR corpus consisting of 50, 000 hours of read English speech derived from LibriVox.
PromptASR for contextualized ASR with controllable style
An additional style prompt can be given to the text encoder and guide the ASR system to output different styles of transcriptions.
Symbol-level Integrated Sensing and Communication enabled Multiple Base Stations Cooperative Sensing
This work may provide a guideline for the design of multi-BS cooperative sensing system to exploit the widely deployed networked mobile communication system.
Delay-penalized CTC implemented based on Finite State Transducer
Our work is open-sourced and publicly available https://github. com/k2-fsa/k2.
Blank-regularized CTC for Frame Skipping in Neural Transducer
Neural Transducer and connectionist temporal classification (CTC) are popular end-to-end automatic speech recognition systems.
Segmentation and Vascular Vectorization for Coronary Artery by Geometry-based Cascaded Neural Network
3) A dataset named CCA-200 is collected, consisting of 200 CCTA images with coronary artery disease.
Knowledge Distillation from Multiple Foundation Models for End-to-End Speech Recognition
The performance of the student model can be further enhanced when multiple teachers are used jointly, achieving word error rate reductions (WERRs) of 17. 5% and 10. 6%.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Intelligent Reflecting Surface assisted Integrated Sensing and Communication System
This paper proves the efficiency of IRS enabled ISAC system, which motivates the implementation of IRS to enhance the sensing capability in ISAC system.
Fast and parallel decoding for transducer
In this work, we introduce a constrained version of transducer loss to learn strictly monotonic alignments between the sequences; we also improve the standard greedy search and beam search algorithms by limiting the number of symbols that can be emitted per time step in transducer decoding, making it more efficient to decode in parallel with batches.
Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation
Although on-the-fly teacher label generation tackles this issue, the training speed is significantly slower as the teacher model has to be evaluated every batch.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Delay-penalized transducer for low-latency streaming ASR
In streaming automatic speech recognition (ASR), it is desirable to reduce latency as much as possible while having minimum impact on recognition accuracy.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Neuro-symbolic Natural Logic with Introspective Revision for Natural Language Inference
We introduce a neuro-symbolic natural logic framework based on reinforcement learning with introspective revision.
Two-Stage is Enough: A Concise Deep Unfolding Reconstruction Network for Flexible Video Compressive Sensing
We consider the reconstruction problem of video compressive sensing (VCS) under the deep unfolding/rolling structure.
Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection
To discover subtle vulnerabilities, we design a powerful attacking algorithm to camouflage rumors in social networks based on reinforcement learning that can interact with and attack any black-box detectors.
Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-trained Models
Self-supervised pre-training is an effective approach to leveraging a large amount of unlabelled data to reduce word error rates (WERs) of automatic speech recognition (ASR) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Exploring Decomposition for Table-based Fact Verification
Fact verification based on structured data is challenging as it requires models to understand both natural language and symbolic operations performed over tables.
Unsupervised Pre-training with Structured Knowledge for Improving Natural Language Inference
There have been two lines of approaches that can be used to further address the limitation: (1) unsupervised pretraining can leverage knowledge in much larger unstructured text data; (2) structured (often human-curated) knowledge has started to be considered in neural-network-based models for NLI.
SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning
Given a passage and the corresponding question, a participating system is expected to choose the correct answer from five candidates of abstract concepts in a cloze-style machine reading comprehension setup.
A High-Dynamic-Range Digital RF-Over-Fiber Link for MRI Receive Coils Using Delta-Sigma Modulation
Non-conductive transmission solutions based on fiber-optic cables are considered to be one of the alternatives, but are limited by the high dynamic range ($>80$~dB) of typical MRI signals.
IA Planner: Motion Planning Using Instantaneous Analysis for Autonomous Vehicle in the Dense Dynamic Scenarios on Highways
In dense and dynamic scenarios, planning a safe and comfortable trajectory is full of challenges when traffic participants are driving at high speed.
Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems
Task-oriented conversational modeling with unstructured knowledge access, as track 1 of the 9th Dialogue System Technology Challenges (DSTC 9), requests to build a system to generate response given dialogue history and knowledge access.
Program Enhanced Fact Verification with Verbalization and Graph Attention Network
Built on that, we construct the graph attention verification networks, which are designed to fuse different sources of evidences from verbalized program execution, program structures, and the original statements and tables, to make the final verification decision.
SemEval-2020 Task 5: Counterfactual Recognition
Subtask-1 aims to determine whether a given sentence is a counterfactual statement or not.
Auxiliary Diagnosing Coronary Stenosis Using Machine Learning
How to accurately classify and diagnose whether an individual has Coronary Stenosis (CS) without invasive physical examination?
Triplet Online Instance Matching Loss for Person Re-identification
Triplet loss processes batch construction in a complicated and fussy way and converges slowly.
