Europe
Hierarchical Optimal Transport for Document Representation
Mikhail Yurochkin, Sebastian Claici, Edward Chien, Farzaneh Mirzazadeh, Justin M. Solomon
Neural Information Processing Systems http://nips.cc/
Amortized Active Causal Induction with Deep Reinforcement Learning
Our design policy successfully achieves amortized intervention design on the distribution of the training environment while also generalizing well to distribution shifts in test-time design environments.
Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning
Erwan Lecarpentier, Emmanuel Rachelson
This work tackles the problem of robust planning in non-stationary stochastic environments.
Numerically Accurate Hyperbolic Embeddings Using Tiling-Based Models
This allows us to learn high-precision embeddings without using BigFloats, and enables us to store the resulting embeddings with fewer bits.
OpenAI's Sam Altman: Global AI regulation 'urgently' needed
OpenAI's Sam Altman: Global AI regulation'urgently' needed OpenAI CEO Sam Altman says the world "urgently" needs global regulation of fast-evolving AI, calling for an international oversight body. The "democratisation of AI is the only fair and safe path forward," he said. Palestinians in Gaza say'Board of Peace' will further occupation Gaza'stabilization force' commander outlines security plans Trump praises'magnificent' B-2 bombers that struck Iran in 2025 Jordan-Israel relationship'at its worst' after West Bank plans Trump's'Board of Peace' convenes for first time Amid tensions, Ukraine's Chernobyl site remains part of a war zone What we know so far about arrest of UK's former Prince Andrew
Towards Automatic Concept-based Explanations
Amirata Ghorbani, James Wexler, James Y. Zou, Been Kim
Neural Information Processing Systems http://nips.cc/
Rest-Katyusha: Exploiting the Solution's Structure via Scheduled Restart Schemes
Junqi Tang, Mohammad Golbabaee, Francis Bach, Mike E. davies
Neural Information Processing Systems http://nips.cc/
Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology
Nima Dehmamy, Albert-Laszlo Barabasi, Rose Yu
Without careful design, GCNs can fail miserably even with multiple layers and nonlinear activation functions.
Reversible, detachable robotic hand redefines dexterity
With its opposable thumb, multiple joints and gripping skin, human hands are often considered to be the pinnacle of dexterity, and many robotic hands are designed in their image. But having been shaped by the slow process of evolution, human hands are far from optimized, with the biggest drawbacks including our single, asymmetrical thumbs and attachment to arms with limited mobility. "We can easily see the limitations of the human hand when attempting to reach objects underneath furniture or behind shelves, or performing simultaneous tasks like holding a bottle while picking up a chip can," says Aude Billard, head of the Learning Algorithms and Systems Laboratory (LASA) in EPFL's School of Engineering. "Likewise, accessing objects positioned behind the hand while keeping the grip stable can be extremely challenging, requiring awkward wrist contortions or body repositioning." A team composed of Billard, LASA researcher Xiao Gao, and Kai Junge and Josie Hughes from the Computational Robot Design and Fabrication Lab designed a robotic hand that overcomes these challenges.