Andrew Lampinen

Aarohi Srivastava, Abhinav Rastogi, Abhishek Rao et al. · allen-ai, amazon-science

Language models demonstrate both quantitative improvement and new qualitative capabilities with increasing scale. Despite their potentially transformative impact, these new capabilities are as yet poorly characterized. In order to inform future research, prepare for disruptive new model capabilities, and ameliorate socially harmful effects, it is vital that we understand the present and near-future capabilities and limitations of language models. To address this challenge, we introduce the Beyond the Imitation Game benchmark (BIG-bench). BIG-bench currently consists of 204 tasks, contributed by 450 authors across 132 institutions. Task topics are diverse, drawing problems from linguistics, childhood development, math, common-sense reasoning, biology, physics, social bias, software development, and beyond. BIG-bench focuses on tasks that are believed to be beyond the capabilities of current language models. We evaluate the behavior of OpenAI's GPT models, Google-internal dense transformer architectures, and Switch-style sparse transformers on BIG-bench, across model sizes spanning millions to hundreds of billions of parameters. In addition, a team of human expert raters performed all tasks in order to provide a strong baseline. Findings include: model performance and calibration both improve with scale, but are poor in absolute terms (and when compared with rater performance); performance is remarkably similar across model classes, though with benefits from sparsity; tasks that improve gradually and predictably commonly involve a large knowledge or memorization component, whereas tasks that exhibit "breakthrough" behavior at a critical scale often involve multiple steps or components, or brittle metrics; social bias typically increases with scale in settings with ambiguous context, but this can be improved with prompting.

Thilo Hagendorff, Ishita Dasgupta, Marcel Binz et al. · deepmind, stanford

Large language models (LLMs) show increasingly advanced emergent capabilities and are being incorporated across various societal domains. Understanding their behavior and reasoning abilities therefore holds significant importance. We argue that a fruitful direction for research is engaging LLMs in behavioral experiments inspired by psychology that have traditionally been aimed at understanding human cognition and behavior. In this article, we highlight and summarize theoretical perspectives, experimental paradigms, and computational analysis techniques that this approach brings to the table. It paves the way for a "machine psychology" for generative artificial intelligence (AI) that goes beyond performance benchmarks and focuses instead on computational insights that move us toward a better understanding and discovery of emergent abilities and behavioral patterns in LLMs. We review existing work taking this approach, synthesize best practices, and highlight promising future directions. We also highlight the important caveats of applying methodologies designed for understanding humans to machines. We posit that leveraging tools from experimental psychology to study AI will become increasingly valuable as models evolve to be more powerful, opaque, multi-modal, and integrated into complex real-world settings.

Viktor Kewenig, Andrew Lampinen, Samuel A. Nastase et al.

The potential of multimodal generative artificial intelligence (mAI) to replicate human grounded language understanding, including the pragmatic, context-rich aspects of communication, remains to be clarified. Humans are known to use salient multimodal features, such as visual cues, to facilitate the processing of upcoming words. Correspondingly, multimodal computational models can integrate visual and linguistic data using a visual attention mechanism to assign next-word probabilities. To test whether these processes align, we tasked both human participants (N = 200) as well as several state-of-the-art computational models with evaluating the predictability of forthcoming words after viewing short audio-only or audio-visual clips with speech. During the task, the model's attention weights were recorded and human attention was indexed via eye tracking. Results show that predictability estimates from humans aligned more closely with scores generated from multimodal models vs. their unimodal counterparts. Furthermore, including an attention mechanism doubled alignment with human judgments when visual and linguistic context facilitated predictions. In these cases, the model's attention patches and human eye tracking significantly overlapped. Our results indicate that improved modeling of naturalistic language processing in mAI does not merely depend on training diet but can be driven by multimodality in combination with attention-based architectures. Humans and computational models alike can leverage the predictive constraints of multimodal information by attending to relevant features in the input.

SIMA team, Adrian Bolton, Alexander Lerchner et al.

We introduce SIMA 2, a generalist embodied agent that understands and acts in a wide variety of 3D virtual worlds. Built upon a Gemini foundation model, SIMA 2 represents a significant step toward active, goal-directed interaction within an embodied environment. Unlike prior work (e.g., SIMA 1) limited to simple language commands, SIMA 2 acts as an interactive partner, capable of reasoning about high-level goals, conversing with the user, and handling complex instructions given through language and images. Across a diverse portfolio of games, SIMA 2 substantially closes the gap with human performance and demonstrates robust generalization to previously unseen environments, all while retaining the base model's core reasoning capabilities. Furthermore, we demonstrate a capacity for open-ended self-improvement: by leveraging Gemini to generate tasks and provide rewards, SIMA 2 can autonomously learn new skills from scratch in a new environment. This work validates a path toward creating versatile and continuously learning agents for both virtual and, eventually, physical worlds.

Arslan Chaudhry, Sridhar Thiagarajan, Andrew Lampinen

Language Models (LMs) exhibit two distinct mechanisms for knowledge acquisition: in-weights learning (i.e., encoding information within the model weights) and in-context learning (ICL). Although these two modes offer complementary strengths, in-weights learning frequently struggles to facilitate deductive reasoning over the internalized knowledge. We characterize this limitation as a deficit in latent generalization, of which the reversal curse is one example. Conversely, in-context learning demonstrates highly robust latent generalization capabilities. To improve latent generalization from in-weights knowledge, prior approaches rely on train-time data augmentation, yet these techniques are task-specific, scale poorly, and fail to generalize to out-of-distribution knowledge. To overcome these shortcomings, this work studies how models can be taught to use test-time compute, or 'thinking', specifically to improve latent generalization. We use Reinforcement Learning (RL) from correctness feedback to train models to produce long chains-of-thought (CoTs) to improve latent generalization. Our experiments show that this thinking approach not only resolves many instances of latent generalization failures on in-distribution knowledge but also, unlike augmentation baselines, generalizes to new knowledge for which no RL was performed. Nevertheless, on pure reversal tasks, we find that thinking does not unlock direct knowledge inversion, but the generate-and-verify ability of thinking models enables them to get well above chance performance. The brittleness of factual self-verification means thinking models still remain well below the performance of in-context learning for this task. Overall, our results establish test-time thinking as a flexible and promising direction for improving the latent generalization of LMs.

Gheorghe Comanici, Eric Bieber, Mike Schaekermann et al. · amazon-science, baidu

In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.

SIMA Team, Maria Abi Raad, Arun Ahuja et al. · deepmind, stanford

Building embodied AI systems that can follow arbitrary language instructions in any 3D environment is a key challenge for creating general AI. Accomplishing this goal requires learning to ground language in perception and embodied actions, in order to accomplish complex tasks. The Scalable, Instructable, Multiworld Agent (SIMA) project tackles this by training agents to follow free-form instructions across a diverse range of virtual 3D environments, including curated research environments as well as open-ended, commercial video games. Our goal is to develop an instructable agent that can accomplish anything a human can do in any simulated 3D environment. Our approach focuses on language-driven generality while imposing minimal assumptions. Our agents interact with environments in real-time using a generic, human-like interface: the inputs are image observations and language instructions and the outputs are keyboard-and-mouse actions. This general approach is challenging, but it allows agents to ground language across many visually complex and semantically rich environments while also allowing us to readily run agents in new environments. In this paper we describe our motivation and goal, the initial progress we have made, and promising preliminary results on several diverse research environments and a variety of commercial video games.

Nicolas Zucchet, Jörg Bornschein, Stephanie Chan et al. · deepmind

Large language models accumulate vast knowledge during pre-training, yet the dynamics governing this acquisition remain poorly understood. This work investigates the learning dynamics of language models on a synthetic factual recall task, uncovering three key findings: First, language models learn in three phases, exhibiting a performance plateau before acquiring precise factual knowledge. Mechanistically, this plateau coincides with the formation of attention-based circuits that support recall. Second, the training data distribution significantly impacts learning dynamics, as imbalanced distributions lead to shorter plateaus. Finally, hallucinations emerge simultaneously with knowledge, and integrating new knowledge into the model through fine-tuning is challenging, as it quickly corrupts its existing parametric memories. Our results emphasize the importance of data distribution in knowledge acquisition and suggest novel data scheduling strategies to accelerate neural network training.

Dan Friedman, Andrew Lampinen, Lucas Dixon et al. · princeton

A common method to study deep learning systems is to use simplified model representations--for example, using singular value decomposition to visualize the model's hidden states in a lower dimensional space. This approach assumes that the results of these simplifications are faithful to the original model. Here, we illustrate an important caveat to this assumption: even if the simplified representations can accurately approximate the full model on the training set, they may fail to accurately capture the model's behavior out of distribution. We illustrate this by training Transformer models on controlled datasets with systematic generalization splits, including the Dyck balanced-parenthesis languages and a code completion task. We simplify these models using tools like dimensionality reduction and clustering, and then explicitly test how these simplified proxies match the behavior of the original model. We find consistent generalization gaps: cases in which the simplified proxies are more faithful to the original model on the in-distribution evaluations and less faithful on various tests of systematic generalization. This includes cases where the original model generalizes systematically but the simplified proxies fail, and cases where the simplified proxies generalize better. Together, our results raise questions about the extent to which mechanistic interpretations derived using tools like SVD can reliably predict what a model will do in novel situations.

Wilka Carvalho, Andrew Lampinen

How can cognitive science build generalizable theories that span the full scope of natural situations and behaviors? We argue that progress in Artificial Intelligence (AI) offers timely opportunities for cognitive science to embrace experiments with increasingly naturalistic stimuli, tasks, and behaviors; and computational models that can accommodate these changes. We first review a growing body of research spanning neuroscience, cognitive science, and AI that suggests that incorporating a broader range of naturalistic experimental paradigms, and models that accommodate them, may be necessary to resolve some aspects of natural intelligence and ensure that our theories generalize. First, we review cases from cognitive science and neuroscience where naturalistic paradigms elicit distinct behaviors or engage different processes. We then discuss recent progress in AI that shows that learning from naturalistic data yields qualitatively different patterns of behavior and generalization, and discuss how these findings impact the conclusions we draw from cognitive modeling, and can help yield new hypotheses for the roots of cognitive and neural phenomena. We then suggest that integrating recent progress in AI and cognitive science will enable us to engage with more naturalistic phenomena without giving up experimental control or the pursuit of theoretically grounded understanding. We offer practical guidance on how methodological practices can contribute to cumulative progress in naturalistic computational cognitive science, and illustrate a path towards building computational models that solve the real problems of natural cognition, together with a reductive understanding of the processes and principles by which they do so.

Jerry Wei, Le Hou, Andrew Lampinen et al.

We present symbol tuning - finetuning language models on in-context input-label pairs where natural language labels (e.g., "positive/negative sentiment") are replaced with arbitrary symbols (e.g., "foo/bar"). Symbol tuning leverages the intuition that when a model cannot use instructions or natural language labels to figure out a task, it must instead do so by learning the input-label mappings. We experiment with symbol tuning across Flan-PaLM models up to 540B parameters and observe benefits across various settings. First, symbol tuning boosts performance on unseen in-context learning tasks and is much more robust to underspecified prompts, such as those without instructions or without natural language labels. Second, symbol-tuned models are much stronger at algorithmic reasoning tasks, with up to 18.2% better performance on the List Functions benchmark and up to 15.3% better performance on the Simple Turing Concepts benchmark. Finally, symbol-tuned models show large improvements in following flipped-labels presented in-context, meaning that they are more capable of using in-context information to override prior semantic knowledge.

Wilka Carvalho, Andrew Lampinen, Kyriacos Nikiforou et al.

Many important tasks are defined in terms of object. To generalize across these tasks, a reinforcement learning (RL) agent needs to exploit the structure that the objects induce. Prior work has either hard-coded object-centric features, used complex object-centric generative models, or updated state using local spatial features. However, these approaches have had limited success in enabling general RL agents. Motivated by this, we introduce "Feature-Attending Recurrent Modules" (FARM), an architecture for learning state representations that relies on simple, broadly applicable inductive biases for capturing spatial and temporal regularities. FARM learns a state representation that is distributed across multiple modules that each attend to spatiotemporal features with an expressive feature attention mechanism. We show that this improves an RL agent's ability to generalize across object-centric tasks. We study task suites in both 2D and 3D environments and find that FARM better generalizes compared to competing architectures that leverage attention or multiple modules.

Adam Santoro, Andrew Lampinen, Kory Mathewson et al.

The ability to use symbols is the pinnacle of human intelligence, but has yet to be fully replicated in machines. Here we argue that the path towards symbolically fluent artificial intelligence (AI) begins with a reinterpretation of what symbols are, how they come to exist, and how a system behaves when it uses them. We begin by offering an interpretation of symbols as entities whose meaning is established by convention. But crucially, something is a symbol only for those who demonstrably and actively participate in this convention. We then outline how this interpretation thematically unifies the behavioural traits humans exhibit when they use symbols. This motivates our proposal that the field place a greater emphasis on symbolic behaviour rather than particular computational mechanisms inspired by more restrictive interpretations of symbols. Finally, we suggest that AI research explore social and cultural engagement as a tool to develop the cognitive machinery necessary for symbolic behaviour to emerge. This approach will allow for AI to interpret something as symbolic on its own rather than simply manipulate things that are only symbols to human onlookers, and thus will ultimately lead to AI with more human-like symbolic fluency.

Felix Hill, Andrew Lampinen, Rosalia Schneider et al.

The question of whether deep neural networks are good at generalising beyond their immediate training experience is of critical importance for learning-based approaches to AI. Here, we consider tests of out-of-sample generalisation that require an agent to respond to never-seen-before instructions by manipulating and positioning objects in a 3D Unity simulated room. We first describe a comparatively generic agent architecture that exhibits strong performance on these tests. We then identify three aspects of the training regime and environment that make a significant difference to its performance: (a) the number of object/word experiences in the training set; (b) the visual invariances afforded by the agent's perspective, or frame of reference; and (c) the variety of visual input inherent in the perceptual aspect of the agent's perception. Our findings indicate that the degree of generalisation that networks exhibit can depend critically on particulars of the environment in which a given task is instantiated. They further suggest that the propensity for neural networks to generalise in systematic ways may increase if, like human children, those networks have access to many frames of richly varying, multi-modal observations as they learn.