· ai
[Paper] Stronger Normalization-Free Transformers
Although normalization layers have long been viewed as indispensable components of deep learning architectures, the recent introduction of Dynamic Tanh (DyT) ha...
-
- · ai
[Paper] On Decision-Making Agents and Higher-Order Causal Processes
We establish a precise correspondence between decision-making agents in partially observable Markov decision processes (POMDPs) and one-input process functions,...
- · ai
[Paper] Empirical evaluation of the Frank-Wolfe methods for constructing white-box adversarial attacks
The construction of adversarial attacks for neural networks appears to be a crucial challenge for their deployment in various services. To estimate the adversar...
- · ai
[Paper] Any4D: Unified Feed-Forward Metric 4D Reconstruction
We present Any4D, a scalable multi-view transformer for metric-scale, dense feed-forward 4D reconstruction. Any4D directly generates per-pixel motion and geomet...
- · ai
[Paper] Curriculum-Based Reinforcement Learning for Autonomous UAV Navigation in Unknown Curved Tubular Conduit
Autonomous drone navigation in confined tubular environments remains a major challenge due to the constraining geometry of the conduits, the proximity of the wa...
- · ai
[Paper] Asynchronous Reasoning: Training-Free Interactive Thinking LLMs
Many state-of-the-art LLMs are trained to think before giving their answer. Reasoning can greatly improve language model capabilities and safety, but it also ma...
- · ai
[Paper] Noisy Quantum Learning Theory
We develop a framework for learning from noisy quantum experiments, focusing on fault-tolerant devices accessing uncharacterized systems through noisy couplings...
- · ai
[Paper] Decoupled Q-Chunking
Temporal-difference (TD) methods learn state and action values efficiently by bootstrapping from their own future value predictions, but such a self-bootstrappi...
- · ai
My journey in the AI agents intensive program...✨
Overview Participating in the Kaggle AI Agents Intensive was a completely new and exciting experience for me. When I joined, I wasn’t fully confident about how...
- · ai
[Paper] Scaling Behavior of Discrete Diffusion Language Models
Modern LLM pre-training consumes vast amounts of compute and training data, making the scaling behavior, or scaling laws, of different models a key distinguishi...
- · ai
[Paper] Generative Modeling from Black-box Corruptions via Self-Consistent Stochastic Interpolants
Transport-based methods have emerged as a leading paradigm for building generative models from large, clean datasets. However, in many scientific and engineerin...
- · ai
[Paper] Bayesian Symbolic Regression via Posterior Sampling
Symbolic regression is a powerful tool for discovering governing equations directly from data, but its sensitivity to noise hinders its broader application. Thi...