Papers that puncture a smaller working assumption inside a field. Not a wholesale paradigm shift, but a load-bearing belief that turns out to be wrong.
Filter by desk: AI Computing Robotics Math Quantum Physics Space Earth Chemistry Engineering Ecology Biology Neuroscience Health Psychology Economics Society
AI
Shows that simple sequential fine-tuning with LoRA outperforms complex algorithms for continual reinforcement learning in VLA models.
AI
Proves that policy gradient algorithms naturally collapse entropy and provides a mathematical fix to preserve exploration and diversity.
AI
Demonstrates that simply using XML tags during translation outperforms complex pipelines for cross-lingual label projection while actually improving translation quality.
AI
Identifies and solves the 'information self-locking' failure mode where RL-trained agents stop asking informative questions in active reasoning tasks.
AI
Shows that LLM self-correction fails primarily due to 'session context' and can be significantly improved by moving the review to a fresh, independent session.
AI
Discovers that task-specific experts are so dense around pretrained weights that random parameter perturbations can compete with complex RL methods like PPO.
AI
Reveals that 'Reasoning LLMs-as-Judges' can lead to policies that generate highly effective adversarial outputs to deceive other judges and inflate benchmarks.
AI
Uncovers an emergent Hue-Saturation-Lightness (HSL) subspace in FLUX.1's VAE latent space, allowing for precise, training-free color control.