6 accepted papers
Best-of-N selection improves reasoning in large language models (LLMs) by allocating additional test-time compute to sample multiple candidate trajectories, but it fundamentally relies on reliable verification. However, widely used proxies based on logit confidence or sample agreement can suffer fro…
Link prediction is a fundamental problem for network-structured data. However, the prevalent research paradigm tends to assume abundant observed links, overlooking more challenging scenarios with a scarcity of observed links, which results in insufficient sample sizes. In real-world networks, hierar…
Incorporating sequence-to-sequence models into history-based Reinforcement Learning (RL) provides a general way to extend RL to partially-observable tasks. This method compresses history spaces according to the correlations between historical observations and the rewards. However, they do not adjust…
Imitation learning (IL) algorithms have shown promising results for robots to learn skills from expert demonstrations. However, they need multi-task demonstrations to be provided at once for acquiring diverse skills, which is difficult in real world. In this work we study how to realize continual im…
Goal-conditioned hierarchical reinforcement learning (HRL) is a promising approach for scaling up reinforcement learning (RL) techniques. However, it often suffers from training inefficiency as the action space of the high-level, i.e., the goal space, is often large. Searching in a large goal space…
Beyond machine learning’s success in the specific tasks, research for learning multiple tasks simultaneously is referred to as multi-task learning. However, existing multi-task learning needs manual definition of tasks and manual task annotation. A crucial problem for advanced intelligence is how to…