Jingrui He

PILL achieves up to 6.0 BLEU-2 improvement on text infilling while running 1.82x faster than the best existing method, revolutionizing efficiency in diffusion language models.

This paper proposes World Model RL (WMRL), which replaces environment execution with a world model to remove this bottleneck and accelerates training by 3-4x on various tasks at different agent scales, while exceeding the performance of standard RL baselines.

Bridging the gap between inference and adaptation in VLMs could lead to significant performance boosts by ensuring robust pseudo-labels that accurately reflect sample-level relationships.

Long-horizon LLM agents can achieve 96.9% task success by learning to adapt their external execution support through trainable harness policies.

The study reveals that maintaining answer accuracy in large models can come at the cost of losing critical reasoning support, highlighting a significant "answer-evidence gap" in KV cache compression.

SafeImpute not only delivers accurate clinical data imputations but also ensures that only reliable results are released, controlling for unacceptable errors.

RECONTEXT boosts long-context reasoning in LLMs by effectively reusing evidence from the input, leading to superior performance without the need for retraining.