19 accepted papers
Long input sequences are central to in-context learning, document understanding, and multi-step reasoning of Large Language Models (LLMs). However, the quadratic attention cost of Transformers makes inference memory-intensive and slow. While context distillation (CD) can transfer information into mo…
So far, expensive finetuning beyond the pretraining sequence length has been a prerequisite to effectively extend the context of language models (LM). In this work, we break this key bottleneck by ***Dro**pping the **P**ositional **E**mbeddings of LMs after training (DroPE)*. Our simple method is mo…
Powerful large language models (LLMs) from different providers have been expensively trained and finetuned to specialize across varying domains. In this work, we introduce a new kind of Conductor model trained with reinforcement learning to automatically discover powerful coordination strategies amo…
We introduce ShinkaEvolve: a new framework leveraging large language models (LLMs) to advance scientific discovery with state-of-the-art performance and efficiency. The field of LLM-driven scientific discovery has seen significant progress, but has yet to overcome a critical limitation: sample ineff…
Scaling autoregressive large language models (LLMs) has had an unprecedented impact, but at vast computational costs. In this work, we tackle these costs by leveraging unstructured sparsity within an LLM's feedforward layers, which account for the majority of its parameters and execution FLOPs. To a…
Combining diverse foundation models is promising, but weight-merging is limited by mismatched architectures and closed APIs. **Trinity** addresses this with a lightweight coordinator that orchestrates collaboration among large language models (LLMs). The coordinator, comprising a compact language mo…
Prior methods propose to offset the escalating costs of modern foundation models by dropping specific parts of their contexts with hand-designed rules, while attempting to preserve their original performance. We overcome this trade-off with Neural Attention Memory Models (NAMMs), introducing a learn…
We propose a new finetuning method to provide pre-trained large language models (LMs) the ability to scale test-time compute through the diffusion framework. By increasing the number of diffusion steps, we show our finetuned models achieve monotonically increasing accuracy, directly translating to i…
Training reasoning language models (LMs) with reinforcement learning (RL) for one-hot correctness inherently relies on the LM being able to explore and solve its task with some chance at initialization. Furthermore, a key use case of reasoning LMs is to act as teachers for distilling new students an…
While Foundation Models provide a general tool for rapid content creation, they regularly require task-specific adaptation. Traditionally, this exercise involves careful curation of datasets and repeated fine-tuning of the underlying model. Fine-tuning techniques enable practitioners to adapt found…
Self-adaptive large language models (LLMs) aim to solve the challenges posed by traditional fine-tuning methods, which are often computationally intensive and static in their ability to handle diverse tasks. We introduce Transformer-Squared, a novel self-adaptation framework that adapts LLMs for uns…
Offline reinforcement learning algorithms have proven effective on datasets highly connected to the target downstream task. Yet, by leveraging a novel testbed (MOOD) in which trajectories come from heterogeneous sources, we show that existing methods struggle with diverse data: their performance con…
Meta-learning holds the potential to provide a general and explicit solution to tackle interference and forgetting in continual learning. However, many popular algorithms introduce expensive and unstable optimization processes with new key hyper-parameters and requirements, hindering their applicabi…
In deep reinforcement learning (RL), useful information about the state is inherently tied to its possible future successors. Consequently, encoding features that capture the hierarchical relationships between states into the model's latent representations is often conducive to recovering effective…
Off-policy deep reinforcement learning algorithms commonly compensate for overestimation bias during temporal-difference learning by utilizing pessimistic estimates of the expected target returns. In this work, we propose Generalized Pessimism Learning (GPL), a strategy employing a novel learnable p…
We introduce a new framework that performs decision-making in reinforcement learning (RL) as an iterative reasoning process. We model agent behavior as the steady-state distribution of a parameterized reasoning Markov chain (RMC), optimized with a new tractable estimate of the policy gradient. We pe…
Off-policy reinforcement learning (RL) from pixel observations is notoriously unstable. As a result, many successful algorithms must combine different domain-specific practices and auxiliary losses to learn meaningful behaviors in complex environments. In this work, we provide novel analysis demonst…
Human beings are able to understand objectives and learn by simply observing others perform a task. Imitation learning methods aim to replicate such capabilities, however, they generally depend on access to a full set of optimal states and actions taken with the agent's actuators and from the agent'…
The performance of reinforcement learning depends upon designing an appropriate action space, where the effect of each action is measurable, yet, granular enough to permit flexible behavior. So far, this process involved non-trivial user choices in terms of the available actions and their execution…