Search Results for author:
Found 20 papers, 5 papers with code
Making Flow-Matching-Based Zero-Shot Text-to-Speech Laugh as You Like
In this work, we propose ELaTE, a zero-shot TTS that can generate natural laughing speech of any speaker based on a short audio prompt with precise control of laughter timing and expression.
Understanding the Weakness of Large Language Model Agents within a Complex Android Environment
These challenges motivate AndroidArena, an environment and benchmark designed to evaluate LLM agents on a modern operating system.
DTMM: Deploying TinyML Models on Extremely Weak IoT Devices with Pruning
DTMM is a library designed for efficient deployment and execution of machine learning models on weak IoT devices such as microcontroller units (MCUs).
PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learning
Designing better deep networks and better reinforcement learning (RL) algorithms are both important for deep RL.
AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes
To the best of our knowledge, AttMOT is the first MOT dataset with semantic attributes.
AGAIN: Adversarial Training With Attribution Span Enlargement and Hybrid Feature Fusion
To this end, compared with standard DNNs, we discover that the generalization gap of adversarially trained DNNs is caused by the smaller attribution span on the input image.
Transformer in Transformer as Backbone for Deep Reinforcement Learning
Recent methods combine the Transformer with these modules for better performance.
AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wild
Multi-animal tracking (MAT), a multi-object tracking (MOT) problem, is crucial for animal motion and behavior analysis and has many crucial applications such as biology, ecology and animal conservation.
Florence: A New Foundation Model for Computer Vision
Computer vision foundation models, which are trained on diverse, large-scale dataset and can be adapted to a wide range of downstream tasks, are critical for this mission to solve real-world computer vision applications.
Ranked #1 on
Action Recognition In Videos
on Kinetics-600
Learning Explicit Credit Assignment for Multi-agent Joint Q-learning
In contrast, we formulate an \emph{explicit} credit assignment problem where each agent gives its suggestion about how to weight individual Q-values to explicitly maximize the joint Q-value, besides guaranteeing the Bellman optimality of the joint Q-value.
Speech-language Pre-training for End-to-end Spoken Language Understanding
End-to-end (E2E) spoken language understanding (SLU) can infer semantics directly from speech signal without cascading an automatic speech recognizer (ASR) with a natural language understanding (NLU) module.
Ranked #3 on
Spoken Language Understanding
on Fluent Speech Commands
(using extra training data)
Reward Design in Cooperative Multi-agent Reinforcement Learning for Packet Routing
In this paper, we study reward design problem in cooperative MARL based on packet routing environments.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Neighborhood Cognition Consistent Multi-Agent Reinforcement Learning
Social psychology and real experiences show that cognitive consistency plays an important role to keep human society in order: if people have a more consistent cognition about their environments, they are more likely to achieve better cooperation.
Learning Agent Communication under Limited Bandwidth by Message Pruning
We evaluate the gating mechanism on several tasks.
Learning Multi-agent Communication under Limited-bandwidth Restriction for Internet Packet Routing
Communication is an important factor for the big multi-agent world to stay organized and productive.
Modelling the Dynamic Joint Policy of Teammates with Attention Multi-agent DDPG
Second, to model the teammates' policies using the collected information in an effective way, ATT-MADDPG enhances the centralized critic with an attention mechanism.
ACCNet: Actor-Coordinator-Critic Net for "Learning-to-Communicate" with Deep Multi-agent Reinforcement Learning
Communication is a critical factor for the big multi-agent world to stay organized and productive.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Predicting Restaurant Consumption Level through Social Media Footprints
Accurate prediction of user attributes from social media is valuable for both social science analysis and consumer targeting.
