arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals […]
[Submitted on 21 Oct 2024 (v1), last revised 17 Apr 2025 (this version, v2)] View a PDF of the paper
[Submitted on 19 Apr 2024 (v1), last revised 17 Apr 2025 (this version, v5)] View a PDF of the paper
Prompting Active Deduction of MLLMs for Assumptive Reasoning Read Post »
[Submitted on 7 Apr 2025 (v1), last revised 17 Apr 2025 (this version, v2)] View a PDF of the paper
[2504.05521] Deep Reinforcement Learning Algorithms for Option Hedging Read Post »
[Submitted on 23 Jan 2025 (v1), last revised 17 Apr 2025 (this version, v2)] View a PDF of the paper
[2501.13810] Learning to Help in Multi-Class Settings Read Post »
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals
Dual-Arm Robot Benchmark with Generative Digital Twins Read Post »
arXiv:2504.12984v1 Announce Type: cross Abstract: Serving Large Language Models (LLMs) is critical for AI-powered applications but demands substantial computational resources,
A Virtual Machine for Arbitrary Low-Precision GPGPU Computation in LLM Serving Read Post »
arXiv:2504.11864v1 Announce Type: new Abstract: Gray-box optimization proposes effective and efficient optimizers of general use. To this end, it leverages
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals
arXiv:2504.11844v1 Announce Type: new Abstract: To what extent do LLMs use their capabilities towards their given goal? We take this
Evaluating the Goal-Directedness of Large Language Models Read Post »