Start Exploring Research Today

Join our community of researchers and gain deeper insights into academic papers.

By subscribing, you agree to our Terms of Service and Privacy Policy.

ESPnet-SpeechLM: An Open Speech Language Model Toolkit

February 21, 2025

| | | | | | | | | | and others

Computer Science
Electrical Engineering and Systems Science
Computation and Language
Sound
Audio and Speech Processing
Computation and Language
Sound
Audio and Speech Processing
We present ESPnet-SpeechLM, an open toolkit designed to democratize the development of speech language models (SpeechLMs) and voice-driven agentic applications. The toolkit standardizes speech processing tasks by framing them as universal s...

FormalSpecCpp: A Dataset of C++ Formal Specifications created using LLMs

February 21, 2025

| | | | |

Computer Science
Software Engineering
Artificial Intelligence
Machine Learning
Programming Languages
Software Engineering
Artificial Intelligence
Machine Learning
Programming Languages
FormalSpecCpp is a dataset designed to fill the gap in standardized benchmarks for verifying formal specifications in C++ programs. To the best of our knowledge, this is the first comprehensive collection of C++ programs with well-defined p...

Approximate weighted 3-coloring

February 21, 2025

| | | | |

Computer Science
Discrete Mathematics
Discrete Mathematics
The paper considers the NP-hard graph vertex coloring problem, which differs from traditional problems in which it is required to color vertices with a given (or minimal) number of colors so that adjacent vertices have different colors. In ...

Tensor Product Neural Networks for Functional ANOVA Model

February 21, 2025

| | | | | | | | |

Statistics
Computer Science
Mathematics
Machine Learning
Machine Learning
Statistics Theory
Statistics Theory
Machine Learning
Machine Learning
Statistics Theory
Statistics Theory
Interpretability for machine learning models is becoming more and more important as machine learning models become more complex. The functional ANOVA model, which decomposes a high-dimensional function into a sum of lower dimensional functi...

The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learning

February 21, 2025

| | | | | | | | | | and others

Computer Science
Machine Learning
Artificial Intelligence
Computation and Language
Machine Learning
Artificial Intelligence
Computation and Language
Reinforcement learning (RL) has shown impressive results in sequential decision-making tasks. Meanwhile, Large Language Models (LLMs) and Vision-Language Models (VLMs) have emerged, exhibiting impressive capabilities in multimodal understan...

The dual Cheeger-Buser inequality for graphons

February 20, 2025

|

Mathematics
Combinatorics
Combinatorics
We introduce the notion of bipartiteness ratio for graphons. We prove the dual Cheeger-Buser inequality for graphons, which relates the gap between 22 and the top of the spectrum of the Laplacian of a graphon with its bipartiteness ratio. ...

Measuring AI agent autonomy: Towards a scalable approach with code inspection

February 20, 2025

| | | | | | | | |

Computer Science
Artificial Intelligence
Artificial Intelligence
AI agents are AI systems that can achieve complex goals autonomously. Assessing the level of agent autonomy is crucial for understanding both their potential benefits and risks. Current assessments of autonomy often focus on specific risks ...

Hierarchical Bayesian estimation of population-level torque law parameters from anomalous pulsar braking indices

February 20, 2025

| | | | |

Physics
High Energy Astrophysical Phenomena
High Energy Astrophysical Phenomena
Abridged. Stochastic fluctuations in the spin frequency ν\nu of a rotation-powered pulsar affect how accurately one measures the power-law braking index, npln_{\rm pl}, defined through ν˙=Kνnpl\dot{\nu}=K\nu^{n_{\rm pl}}, and can lead to measurem...

PairBench: A Systematic Framework for Selecting Reliable Judge VLMs

February 20, 2025

| | | | | | | | | | and others

Computer Science
Machine Learning
Artificial Intelligence
Computation and Language
Machine Learning
Artificial Intelligence
Computation and Language
As large vision language models (VLMs) are increasingly used as automated evaluators, understanding their ability to effectively compare data pairs as instructed in the prompt becomes essential. To address this, we present PairBench, a low-...

Birkhoff sections in 3-manifold with invariant toric foliation

February 20, 2025

|

Mathematics
Dynamical Systems
Dynamical Systems
In this paper, we propose a method for directly constructing Birkhoff sections on 3-manifolds foliated by invariant tori. We establish the necessary and sufficient conditions for various types of periodic orbits to serve as boundary orbits ...