Author name cluster

Edoardo Cetin

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

14 papers

2 author rows

ICLR Conference 2025 Conference Paper

An Evolved Universal Transformer Memory

Edoardo Cetin
Qi Sun
Tianyu Zhao 0001
Yujin Tang

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 learned network for memory management that improves both the performance and efficiency of transformers. We evolve NAMMs atop pre-trained transformers to provide different latent contexts focusing on the most relevant information for individual layers and attention heads. NAMMs are universally applicable to any model using self-attention as they condition exclusively on the values in the produced attention matrices. Learning NAMMs on a small set of problems, we achieve substantial performance improvements across multiple long-context benchmarks while cutting the model's input contexts up to a fraction of the original sizes. We show the generality of our conditioning enables zero-shot transfer of NAMMs trained only on language to entirely new transformer architectures even across input modalities, with their benefits carrying over to vision and reinforcement learning.

Details

RLJ Journal 2025 Journal Article

Finer Behavioral Foundation Models via Auto-Regressive Features and Advantage Weighting

Edoardo Cetin
Ahmed Touati
Yann Ollivier

The forward-backward representation (FB) is a recently proposed framework (Touati et al., 2023; Touati and Ollivier, 2021) to train be- havior foundation models (BFMs) that aim at providing zero-shot efficient policies for any new task specified in a given reinforcement learning (RL) environment, without training for each new task. Here we address two core limitations of FB model training First, FB, like all successor-feature-based methods, relies on a linear encoding of tasks: at test time, each new reward function is linearly projected onto a fixed set of pre- trained features. This limits expressivity as well as precision of the task representation. We break the linearity limitation by introduc- ing auto-regressive features for FB, which let fine-grained task features depend on coarser- grained task information. This can represent arbitrary nonlinear task encodings, thus sig- nificantly increasing expressivity of the FB framework. Second, it is well-known that training RL agents from offline datasets often requires spe- cific techniques.We show that FB works well together with such offline RL techniques, by adapting techniques from (Nair et al., 2020a; Cetin et al., 2024) for FB. This is necessary to get non-flatlining performance in some datasets, such as DMC Humanoid. As a result, we produce efficient FB BFMs for a number of new environments. Notably, in the D4RL locomotion benchmark, the generic FB agent matches the performance of stan- dard single-task offline agents (IQL, XQL). In many setups, the offline techniques are needed to get any decent performance at all. The auto-regressive features have a positive but moderate impact, concentrated on tasks requiring spatial precision and task general- ization beyond the behaviors represented in the trainset. Together, these results establish that generic, reward-free FB BFMs can be competitive with single-task agents on standard benchmarks, while suggesting that expressivity of the BFM is not a key limiting factor in the environments tested.

PDF Details

RLC Conference 2025 Conference Paper

Finer Behavioral Foundation Models via Auto-Regressive Features and Advantage Weighting

Edoardo Cetin
Ahmed Touati
Yann Ollivier

The forward-backward representation (FB) is a recently proposed framework (Touati et al. , 2023; Touati and Ollivier, 2021) to train be- havior foundation models (BFMs) that aim at providing zero-shot efficient policies for any new task specified in a given reinforcement learning (RL) environment, without training for each new task. Here we address two core limitations of FB model training First, FB, like all successor-feature-based methods, relies on a linear encoding of tasks: at test time, each new reward function is linearly projected onto a fixed set of pre- trained features. This limits expressivity as well as precision of the task representation. We break the linearity limitation by introduc- ing auto-regressive features for FB, which let fine-grained task features depend on coarser- grained task information. This can represent arbitrary nonlinear task encodings, thus sig- nificantly increasing expressivity of the FB framework. Second, it is well-known that training RL agents from offline datasets often requires spe- cific techniques. We show that FB works well together with such offline RL techniques, by adapting techniques from (Nair et al. , 2020a; Cetin et al. , 2024) for FB. This is necessary to get non-flatlining performance in some datasets, such as DMC Humanoid. As a result, we produce efficient FB BFMs for a number of new environments. Notably, in the D4RL locomotion benchmark, the generic FB agent matches the performance of stan- dard single-task offline agents (IQL, XQL). In many setups, the offline techniques are needed to get any decent performance at all. The auto-regressive features have a positive but moderate impact, concentrated on tasks requiring spatial precision and task general- ization beyond the behaviors represented in the trainset. Together, these results establish that generic, reward-free FB BFMs can be competitive with single-task agents on standard benchmarks, while suggesting that expressivity of the BFM is not a key limiting factor in the environments tested.

PDF Details

ICML Conference 2025 Conference Paper

Large Language Models to Diffusion Finetuning

Edoardo Cetin
Tianyu Zhao 0001
Yujin Tang

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 improved performance across downstream tasks. Furthermore, our finetuned models can expertly answer questions on specific topics by integrating powerful guidance techniques, and autonomously determine the compute required for a given problem by leveraging adaptive ODE solvers. Our method is applicable to any foundation model pre-trained with cross-entropy and does not modify any of its original weights, fully preserving its strong single-step generation capabilities. We show our method can be more effective and is fully compatible with traditional finetuning and search approaches, introducing an orthogonal new direction to unify the strengths of the autoregressive and diffusion frameworks.

Details

NeurIPS Conference 2025 Conference Paper

Reinforcement Learning Teachers of Test Time Scaling

Edoardo Cetin
Tianyu Zhao
Yujin Tang

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 and cold-starting future RL iterations rather than being deployed themselves. From these considerations, we introduce a new framework that avoids RL's exploration challenge by training a new class of Reinforcement-Learned Teachers (RLTs) focused on yielding the most effective downstream distillation. RLTs are prompted with both the question and solution to each problem, and tasked to simply "connect-the-dots" with detailed explanations tailored for their students. We train RLTs with dense rewards obtained by feeding each explanation to the student and testing its understanding of the problem's solution. In practice, the raw outputs of a 7B RLT provide higher final performance on competition and graduate-level tasks than existing distillation and cold-starting pipelines that collect and postprocess the reasoning traces of orders of magnitude larger LMs. Furthermore, RLTs maintain their effectiveness when training larger students and when applied zero-shot to out-of-distribution tasks, unlocking new levels of efficiency and re-usability for the RL reasoning framework.

PDF Details

ICML Conference 2025 Conference Paper

Text-to-LoRA: Instant Transformer Adaption

Rujikorn Charakorn
Edoardo Cetin
Yujin Tang
Robert Tjarko Lange

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 foundation models for many new applications but require expensive and lengthy training while being notably sensitive to hyperparameter choices. To overcome these limitations, we introduce Text-to-LoRA (T2L), a model capable of adapting large language models (LLMs) on the fly solely based on a natural language description of the target task. T2L is a hypernetwork trained to construct LoRAs in a single inexpensive forward pass. After training T2L on a suite of 9 pre-trained LoRA adapters (GSM8K, Arc, etc.), we show that the ad-hoc reconstructed LoRA instances match the performance of task-specific adapters across the corresponding test sets. Furthermore, T2L can compress hundreds of LoRA instances and zero-shot generalize to entirely unseen tasks. This approach provides a significant step towards democratizing the specialization of foundation models and enables language-based adaptation with minimal compute requirements. Our code is available at https: //github. com/SakanaAI/text-to-lora

Details

ICLR Conference 2025 Conference Paper

Transformer-Squared: Self-adaptive LLMs

Qi Sun
Edoardo Cetin
Yujin Tang

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 unseen tasks in real-time by selectively adjusting only the singular components of their weight matrices. During inference, Transformer-Squared employs a two-pass mechanism: first, a dispatch system identifies the task properties, and then task-specific 'expert' vectors, trained using reinforcement learning, are dynamically mixed to obtain targeted behavior for the incoming prompt. Our method consistently outperforms ubiquitous approaches such as LoRA, with fewer parameters and greater efficiency. Furthermore, Transformer-Squared demonstrates versatility across different LLM architectures and modalities, including vision-language tasks. Transformer-Squared represents a significant leap forward, offering a scalable, efficient solution for enhancing the adaptability and task-specific performance of LLMs, paving the way for truly dynamic, self-organizing AI systems.

Details

ICML Conference 2024 Conference Paper

Simple Ingredients for Offline Reinforcement Learning

Edoardo Cetin
Andrea Tirinzoni
Matteo Pirotta
Alessandro Lazaric
Yann Ollivier
Ahmed Touati

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 considerably deteriorates as data collected for related but different tasks is simply added to the offline buffer. In light of this finding, we conduct a large empirical study where we formulate and test several hypotheses to explain this failure. Surprisingly, we find that targeted scale, more than algorithmic considerations, is the key factor influencing performance. We show that simple methods like AWAC and IQL with increased policy size overcome the paradoxical failure modes from the inclusion of additional data in MOOD, and notably outperform prior state-of-the-art algorithms on the canonical D4RL benchmark.

Details

ICLR Conference 2023 Conference Paper

Hyperbolic Deep Reinforcement Learning

Edoardo Cetin
Ben Chamberlain 0001
Michael M. Bronstein
Jonathan J. Hunt

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 policies. In this work, we study a new class of deep RL algorithms that promote encoding such relationships by using hyperbolic space to model latent representations. However, we find that a naive application of existing methodology from the hyperbolic deep learning literature leads to fatal instabilities due to the non-stationarity and variance characterizing common gradient estimators in RL. Hence, we design a new general method that directly addresses such optimization challenges and enables stable end-to-end learning with deep hyperbolic representations. We empirically validate our framework by applying it to popular on-policy and off-policy RL algorithms on the Procgen and Atari 100K benchmarks, attaining near universal performance and generalization benefits. Given its natural fit, we hope this work will inspire future RL research to consider hyperbolic representations as a standard tool.

Details

AAAI Conference 2023 Conference Paper

Learning Pessimism for Reinforcement Learning

Edoardo Cetin
Oya Celiktutan

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 penalty to enact such pessimism. In particular, we propose to learn this penalty alongside the critic with dual TD-learning, a new procedure to estimate and minimize the magnitude of the target returns bias with trivial computational cost. GPL enables us to accurately counteract overestimation bias throughout training without incurring the downsides of overly pessimistic targets. By integrating GPL with popular off-policy algorithms, we achieve state-of-the-art results in both competitive proprioceptive and pixel-based benchmarks.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

Policy Gradient With Serial Markov Chain Reasoning

Edoardo Cetin
Oya Celiktutan

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 perform action selection by simulating the RMC for enough reasoning steps to approach its steady-state distribution. We show our framework has several useful properties that are inherently missing from traditional RL. For instance, it allows agent behavior to approximate any continuous distribution over actions by parameterizing the RMC with a simple Gaussian transition function. Moreover, the number of reasoning steps to reach convergence can scale adaptively with the difficulty of each action selection decision and can be accelerated by re-using past solutions. Our resulting algorithm achieves state-of-the-art performance in popular Mujoco and DeepMind Control benchmarks, both for proprioceptive and pixel-based tasks.

PDF Details

ICML Conference 2022 Conference Paper

Stabilizing Off-Policy Deep Reinforcement Learning from Pixels

Edoardo Cetin
Philip J. Ball
Stephen J. Roberts
Oya Çeliktutan

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 demonstrating that these instabilities arise from performing temporal-difference learning with a convolutional encoder and low-magnitude rewards. We show that this new visual deadly triad causes unstable training and premature convergence to degenerate solutions, a phenomenon we name catastrophic self-overfitting. Based on our analysis, we propose A-LIX, a method providing adaptive regularization to the encoder’s gradients that explicitly prevents the occurrence of catastrophic self-overfitting using a dual objective. By applying A-LIX, we significantly outperform the prior state-of-the-art on the DeepMind Control and Atari benchmarks without any data augmentation or auxiliary losses.

Details

ICLR Conference 2021 Conference Paper

Domain-Robust Visual Imitation Learning with Mutual Information Constraints

Edoardo Cetin
Oya Çeliktutan

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's point of view. In this paper, we introduce a new algorithm - called Disentangling Generative Adversarial Imitation Learning (DisentanGAIL) - with the purpose of bypassing such constraints. Our algorithm enables autonomous agents to learn directly from high dimensional observations of an expert performing a task, by making use of adversarial learning with a latent representation inside the discriminator network. Such latent representation is regularized through mutual information constraints to incentivize learning only features that encode information about the completion levels of the task being demonstrated. This allows to obtain a shared feature space to successfully perform imitation while disregarding the differences between the expert's and the agent's domains. Empirically, our algorithm is able to efficiently imitate in a diverse range of control problems including balancing, manipulation and locomotive tasks, while being robust to various domain differences in terms of both environment appearance and agent embodiment.

Details

ICML Conference 2021 Conference Paper

Learning Routines for Effective Off-Policy Reinforcement Learning

Edoardo Cetin
Oya Çeliktutan

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 frequency. We propose a novel framework for reinforcement learning that effectively lifts such constraints. Within our framework, agents learn effective behavior over a routine space: a new, higher-level action space, where each routine represents a set of ’equivalent’ sequences of granular actions with arbitrary length. Our routine space is learned end-to-end to facilitate the accomplishment of underlying off-policy reinforcement learning objectives. We apply our framework to two state-of-the-art off-policy algorithms and show that the resulting agents obtain relevant performance improvements while requiring fewer interactions with the environment per episode, improving computational efficiency.

Details