Country
The functional specialization of visual cortex emerges from training parallel pathways with self-supervised predictive learning
In particular, the clearest example is the specialization of the ventral ("what") and dorsal
Asymmetric Valleys: Beyond Sharp and Flat Local Minima
Haowei He, Gao Huang, Yang Yuan
Neural Information Processing Systems http://nips.cc/
Explainable and Efficient Randomized Voting Rules
With a rapid growth in the deployment of AI tools for making critical decisions (or aiding humans in doing so), there is a growing demand to be able to explain to the stakeholders how these tools arrive at a decision.
Exact Gaussian Processes on a Million Data Points
Ke Wang, Geoff Pleiss, Jacob Gardner, Stephen Tyree, Kilian Q. Weinberger, Andrew Gordon Wilson
Neural Information Processing Systems http://nips.cc/
Fast Best-of-N Decoding via Speculative Rejection Hanshi Sun
The safe and effective deployment of Large Language Models (LLMs) involves a critical step called alignment, which ensures that the model's responses are in accordance with human preferences. Prevalent alignment techniques, such as DPO, PPO and their variants, align LLMs by changing the pre-trained model weights during a phase called post-training. While predominant, these post-training methods add substantial complexity before LLMs can be deployed. Inference-time alignment methods avoid the complex post-training step and instead bias the generation towards responses that are aligned with human preferences. The best-known inference-time alignment method, called Best-of-N, is as effective as the state-of-the-art post-training procedures. Unfortunately, Best-of-N requires vastly more resources at inference time than standard decoding strategies, which makes it computationally not viable.
