We model episode sessions--parts of the episode where the latent state isfixed--and propose three keymodifications toexisting meta-RL methods: (i) consistency of latent information within sessions, (ii) session masking, and (iii) priorlatent conditioning.

Differential privacyisthedominant standard forformal andquantifiable privacy and has been used in major deployments that impact millions of people.

Inference via knowledge compilation has also been used for many applications in neuro-symbolic AI,suchasconstrained generation [2,54]andneural logic programming [34,28].

In this paper, we present DSA, the first automated framework for discovering sparsity allocation schemes for layer-wise pruning in Large Language Models (LLMs). LLMs have become increasingly powerful, but their large parameter counts make them computationally expensive. Existing pruning methods for compressing LLMs primarily focus on evaluating redundancies and removing element-wise weights. However, these methods fail to allocate adaptive layerwise sparsities, leading to performance degradation in challenging tasks.

Open-vocabulary 3D object detection (OV-3Det) aims to generalize beyond the limited number ofbasecategories labeled during thetraining phase. Thebiggest bottleneck is the scarcity of annotated 3D data, whereas 2D image datasets are abundantandrichlyannotated.

Inthiswork,wepresentBAKU,asimple transformer architecture that enables efficient learning of multi-task robot policies.BAKU builds upon recent advancements in offline imitation learning and meticulously combines observation trunks, action chunking, multi-sensory observations, and action heads tosubstantially improveupon prior work.