相关论文: Improving Token-Based World Models with Parallel O…

We consider a sequential decision making problem where the agent faces the environment characterized by the stochastic discrete events and seeks an optimal intervention policy such that its long-term reward is maximized. This problem exists…

Current language models (LMs) use a fixed, static subword tokenizer. This default choice typically results in degraded efficiency and language capabilities, especially in languages other than English. To address this issue, we challenge the…

Gradient-based optimizers are highly sensitive to design choices in their adaptive learning rate mechanisms. To address this limitation, we introduce POP, a meta-learned Reinforcement Learning (RL) policy that predicts adaptive learning…

Unified models aim to support both understanding and generation by encoding images into discrete tokens and processing them alongside text within a single autoregressive framework. This unified design offers architectural simplicity and…

Generative transformer models have become increasingly complex, with large numbers of parameters and the ability to process multiple input modalities. Current methods for explaining their predictions are resource-intensive. Most crucially,…

Despite the remarkable strides made by autoregressive language models, their potential is often hampered by the slow inference speeds inherent in sequential token generation. Blockwise parallel decoding (BPD) was proposed by Stern et al. as…

In recent years, Model-based Multi-Agent Reinforcement Learning (MARL) has demonstrated significant advantages over model-free methods in terms of sample efficiency by using independent environment dynamics world models for data sample…

Continual RL requires an agent to learn new tasks without forgetting previous ones, while improving on both past and future tasks. The most common approaches use model-free algorithms and replay buffers can help to mitigate catastrophic…

Restricted Boltzmann Machines (RBMs) are generative models which can learn useful representations from samples of a dataset in an unsupervised fashion. They have been widely employed as an unsupervised pre-training method in machine…

Counting repetitive actions in long untrimmed videos is a challenging task that has many applications such as rehabilitation. State-of-the-art methods predict action counts by first generating a temporal self-similarity matrix (TSM) from…

Generative recommendation (GenRec) models typically model user behavior via full attention, but scaling to lifelong sequences is hindered by prohibitive computational costs and noise accumulation from stochastic interactions. To address…

This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories. The compute for pre-training LLMs has been growing at an…

Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token decoding mechanism inherent in traditional autoregressive…

While modern policy optimization methods can do complex manipulation from sensory data, they struggle on problems with extended time horizons and multiple sub-goals. On the other hand, task and motion planning (TAMP) methods scale to long…

The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an additional intermediate stage called reinforcement mid-training…

Temporal action proposal generation (TAPG) aims to estimate temporal intervals of actions in untrimmed videos, which is a challenging yet plays an important role in many tasks of video analysis and understanding. Despite the great…

Masked video modeling~(MVM) has emerged as a highly effective pre-training strategy for visual foundation models, whereby the model reconstructs masked spatiotemporal tokens using information from visible tokens. However, a key challenge in…

Reinforcement learning allows solving complex tasks, however, the learning tends to be task-specific and the sample efficiency remains a challenge. We present Plan2Explore, a self-supervised reinforcement learning agent that tackles both…

Multimodal large language models (MLLMs) demonstrate strong performance across visual tasks, but their efficiency is hindered by significant computational and memory demands from processing long contexts in multimodal inputs. To address…

We study reinforcement learning for global decision-making in the presence of local agents, where the global decision-maker makes decisions affecting all local agents, and the objective is to learn a policy that maximizes the joint rewards…