Query-Conditioned Test-Time Self-Training for Large Language Models
arXiv:2605.13369v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are typically deployed with fixed parameters, and their performance is often…
A strong sustainability approach to AI development
Nature Machine Intelligence, Published online: 15 May 2026; doi:10.1038/s42256-026-01240-w A strong sustainability approach to AI development
Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents
arXiv:2605.12620v1 Announce Type: new Abstract: Building generalist embodied agents capable of solving complex real-world tasks remains a fundamental challenge in…
A New Technique for AI Explainability using Feature Association Map
arXiv:2605.12350v2 Announce Type: replace-cross Abstract: Lack of transparency in AI systems poses challenges in critical real-life applications. It is important…
Q-Flow: Stable and Expressive Reinforcement Learning with Flow-Based Policy
arXiv:2605.13435v1 Announce Type: cross Abstract: There is growing interest in utilizing flow-based models as decision-making policies in reinforcement learning due…
Towards a holistic understanding of Selection Bias for Causal Effect Identification
arXiv:2605.13430v1 Announce Type: cross Abstract: Selection bias is pervasive in observational studies. For example, large scale biobanks data can exhibit…
Gradient-Free Noise Optimization for Reward Alignment in Generative Models
arXiv:2605.11347v2 Announce Type: replace-cross Abstract: Existing reward alignment methods for diffusion and flow models rely on multi-step stochastic trajectories, making…