Search Results for author:
Found 11 papers, 3 papers with code
A Survey of AI Agent Protocols
We expect this work to serve as a practical reference for both researchers and engineers seeking to design, evaluate, or integrate robust communication infrastructures for intelligent agents.
MARFT: Multi-Agent Reinforcement Fine-Tuning
Central to this work is a robust and scalable MARFT framework.
Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision
Extensive experiments validate the efficacy of our pipeline, yielding the following key findings:(1) In the visual understanding task, Nexus exhibits superior performance compared with its backbone model - Qwen2. 5-VL-7B, validating the efficiency of our training strategy.
Agentic Information Retrieval
Information state refers to a particular information context that the user is right in within a dynamic environment, encompassing not only the acquired information items but also real-time user preferences, contextual factors, and decision-making processes.
Hammer: Robust Function-Calling for On-Device Language Models via Function Masking
Large language models have demonstrated impressive value in performing as autonomous agents when equipped with external tools and API calls.
Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement
We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks; results underline ETPO's potential as a robust method for refining the interactive decision-making capabilities of language agents.
SkillNet-NLG: General-Purpose Natural Language Generation with a Sparsely Activated Approach
We present SkillNet-NLG, a sparsely activated approach that handles many natural language generation tasks with one model.
Pretraining without Wordpieces: Learning Over a Vocabulary of Millions of Words
(2) how to predict a word via cloze test without knowing the number of wordpieces in advance?
Generating Human Readable Transcript for Automatic Speech Recognition with Pre-trained Language Model
Many downstream tasks and human readers rely on the output of the ASR system; therefore, errors introduced by the speaker and ASR system alike will be propagated to the next task in the pipeline.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Improving Readability for Automatic Speech Recognition Transcription
In this work, we propose a novel NLP task called ASR post-processing for readability (APR) that aims to transform the noisy ASR output into a readable text for humans and downstream tasks while maintaining the semantic meaning of the speaker.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
