AdvWeb: Controllable Black-box Attacks on VLM-powered Web Agents
【DL輪読会】AdvWeb: Controllable Black-box Attacks on VLM-powered Web Agents by @DeepLearn more
Category:
A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
【DL輪読会】 “A Real-World WebAgent with Planning, Long Context Understanding, and Program more
Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents
【DL輪読会】Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI more
A Foundation of Reinforcement Learning for StochasticContinuous Dynamics:Temporal Difference Method
【DL輪読会】A Foundation of Reinforcement Learning for StochasticContinuous Dynamics:Tempo more
Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form (ICLR2025)
Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes vi more
PhysBench: Benchmarking and Enhancing Vision-Langauge Models for Physical World Understanding
https://www.docswell.com/s/DeepLearning2023/ZQR4GN-2025-03-13-145315
Improving the Diffusability of Autoencoders
https://www.docswell.com/s/DeepLearning2023/53GYPL-2025-03-13-144306
Masked Diffusion Modelの進展
<script async class=”docswell-embed” src=”https://www.docswell.c more
Classification of the Fashion-MNIST Dataset on a Quantum Computer
【DL輪読会】Classification of the Fashion-MNIST Dataset on a Quantum Computer by @DeepLear more
Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operators
【DL輪読会】Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary d more