ICLR 2026 Papers

Imitation Learning (IL) enables agents to mimic expert behavior by learning from demonstrations. However, traditional IL methods require large amounts of medium-to-high-quality demonstrations as well as actions of expert demonstrations, both of which are often unavailable. To reduce this need, we propose Latent Wasserstein Adversarial Imitation Learning (LWAIL), a novel adversarial imitation learning framework that focuses on state-only distribution matching. It benefits from the Wasserstein distance computed in a dynamics-aware latent space. This dynamics-aware latent space differs from prior work and is obtained via a pre-training stage, where we train the Intention Conditioned Value Function (ICVF) to capture a dynamics-aware structure of the state space using a small set of randomly generated state-only data. We show that this enhances the policy's understanding of state transitions, enabling the learning process to use only one or a few state-only expert episodes to achieve expert-level performance. Through experiments on multiple MuJoCo environments, we demonstrate that our method outperforms prior Wasserstein-based IL methods and prior adversarial IL methods, achieving better results across various tasks.

Real-world deployment of machine learning models requires the ability to continually learn from non-stationary data while preserving prior knowledge and user privacy. Therefore, storing knowledge acquired from past data in a resource- and privacy-friendly manner is a crucial consideration in determining their viability. We introduce Quantized Gradient Projection Memory (QGPM), a systematic framework for continual learning that compresses and preserves the previous gradient subspace. QGPM integrates three key components: (i) distribution-aware, basis-wise quantization to minimize storage overhead, (ii) a Quantization Error-Aware (QEA) gradient projection that selectively relaxes orthogonality to mitigate gradient drift caused by accumulated quantization noise, and (iii) an on-the-fly sparse sketching strategy that improves runtime memory and computational efficiency. Experiments across multiple benchmarks demonstrate that QGPM achieves state-of-the-art performance under fixed memory budgets, highlighting its effectiveness in scalable, privacy-preserving continual learning.

Machine unlearning is studied for a multitude of tasks, but specialization of unlearning methods to particular tasks has made their systematic comparison challenging. To address this issue, we propose a conceptual space to characterize diverse corrupted data unlearning tasks in vision classifiers. This space is described by two dimensions, the discovery rate (the fraction of the corrupted data that are known at unlearning time) and the statistical regularity of the corrupted data (from random exemplars to shared concepts). Methods proposed previously have been targeted at portions of this space and, as we show, fail predictably outside these regions. We propose Redirection for Erasing Memory (REM), whose key feature is that corrupted data are redirected to dedicated neurons introduced at unlearning time and then discarded or deactivated to suppress the influence of corrupted data. REM performs strongly across the space of tasks, in contrast to prior SOTA methods that fail outside the regions for which they were designed.

Modern neural sequence models are designed to meet the dual mandate of parallelizable training and fast sequential inference. Recent developments have given rise to various models, such as Gated Linear Attention (GLA) and Mamba, that achieve such ``sequential-parallel duality.'' This raises a natural question: can we characterize the full class of neural sequence models that support near-constant-time parallel evaluation and linear-time, constant-space sequential inference? We begin by describing a broad class of such models -- state space models -- as those whose state updates can be computed using the classic parallel prefix scan algorithm with a custom associative aggregation operator. We then define a more general class, Prefix-Scannable Models (PSMs), by relaxing the state aggregation operator to allow arbitrary (potentially non-associative) functions such as softmax attention. This generalization unifies many existing architectures, including element-wise RNNs (e.g., Mamba) and linear transformers (e.g., GLA, Mamba2, mLSTM), while also introducing new models with softmax-like operators that achieve O(1) amortized compute per token and log(N) memory for sequence length N. We empirically evaluate such models on illustrative small-scale language modeling and canonical synthetic tasks, including state tracking and associative recall. Empirically, we find that PSMs retain the expressivity of transformer-based architectures while matching the inference efficiency of state space models -- in some cases exhibiting better length generalization than either.

State Space Models (SSMs) have become the leading alternative to Transformers for sequence modeling tasks. Their primary advantage is efficiency in long-context and long-form generation, enabled by fixed-size memory and linear scaling of computational complexity. We begin this work by showing a simple theoretical result stating that SSMs cannot accurately solve any long-form generation problem, undermining their main competitive advantage. However, we show that this limitation can be mitigated by allowing SSMs interactive access to external tools. In fact, we show that given the right choice of tool access and problem-dependent training data, SSMs can learn to solve any tractable problem and generalize to arbitrary problem length/complexity (i.e., achieve length generalization). Following our theoretical finding, we demonstrate that tool-augmented SSMs achieve remarkable length generalization on a variety of arithmetic, reasoning, and coding tasks. These findings highlight SSMs as a potential efficient alternative to Transformers in interactive tool-based and agentic settings.

End-to-end backpropagation requires storing activations throughout all layers, creating memory bottlenecks that limit model scalability. Existing block-wise training methods offer means to alleviate this problem, but they rely on ad-hoc local objectives and remain largely unexplored beyond classification tasks. We propose $\textit{DiffusionBlocks}$, a principled framework for transforming transformer-based networks into genuinely independent trainable blocks that maintain competitive performance with end-to-end training. Our key insight leverages the fact that residual connections naturally correspond to updates in a dynamical system. With minimal modifications to this system, we can convert the updates to those of a denoising process, where each block can be learned independently by leveraging the score matching objective. This independence enables training with gradients for only one block at a time, thereby reducing memory requirements in proportion to the number of blocks. Our experiments on a range of transformer architectures (vision, diffusion, autoregressive, recurrent-depth, and masked diffusion) demonstrate that DiffusionBlocks training matches the performance of end-to-end training while enabling scalable block-wise training on practical tasks beyond small-scale classification. DiffusionBlocks provides a theoretically grounded approach that successfully scales to modern generative tasks across diverse architectures.

Recent advances in sequence modeling have highlighted Mamba as a state space architecture offering efficient long-range dependency modeling and providing a viable alternative to Transformers. Building upon this, Mamba-2 introduces the Structured State Space Duality (SSD), which integrates recurrent and attention modes to achieve efficiency and scalability. However, this architectural expansion substantially increases memory and latency overhead, underscoring the need for efficient compression strategies tailored to SSD. In this work, we present SSDi8, the first post-training quantization framework specifically designed for SSD to maintain a persistent INT8 path. SSDi8 introduces a reformulation that decouples element-wise multiplications from matrix multiplications, enabling reuse of quantized activations across modules. Moreover, SSDi8 adaptively quantizes channel-varying activations at cost-effective points, further reducing latency. On the accuracy side, SSDi8 explicitly leverages the intrinsic dimensional decomposition of SSD, exploiting distinct outlier distributions across axes, and incorporates an error correction term based on per-channel error statistics. Comprehensive experiments demonstrate that SSDi8 achieves accuracy comparable to FP16 while delivering up to 1.4X speedup in W4A8 and W8A8 settings. We further validate its robustness in resource-constrained environments by deploying it on the Orin Nano device.

Large language models, constrained by the fixed-depth Transformer architecture, struggle to solve complex reasoning tasks in an end-to-end manner. Existing approaches, such as Chain of Thought, improve reasoning depth to some extent but rely heavily on natural language generation, with computational costs increasing rapidly as the length of the generated sequence grows. To address these limitations, we propose ChainGPT, a dual-reasoning model that shifts reasoning into latent computational space. Within each layer, ChainGPT employs multi-substep state updates combined with state-guided sparse attention, enabling deep local computation and efficient long-range modeling without quadratic costs. Across layers, recurrent depth approach iteratively refine latent states, supported by adaptive training and stopping strategies that balance reasoning depth against computational budget. Theoretically, we show that ChainGPT can, in principle, simulate general computation, and empirically it delivers consistent improvements over comparable models, including on reasoning tasks that remain challenging for existing systems. By unifying efficiency and reasoning ability, ChainGPT provides a principled foundation for next-generation language models.

Understanding how long-term stimulation reshapes neural circuits requires uncovering the rules of brain plasticity. While short-term synaptic modifications have been extensively characterized, the principles that drive circuit-level reorganization across hours to weeks remain unknown. Here, we formalize these principles as a latent dynamical law that governs how recurrent connectivity evolves under repeated interventions. To capture this law, we introduce the Stimulus-Evoked Evolution Recurrent dynamics (STEER) framework, a dual-timescale model that disentangles fast neural activity from slow plastic changes. STEER represents plasticity as low-dimensional latent coefficients evolving under a learnable recurrence, enabling testable inference of plasticity rules rather than absorbing them into black-box parameters. We validate STEER with four benchmarks: synthetic Lorenz systems with controlled parameter shifts, BCM-based networks with biologically grounded plasticity, a task learning setting with adaptively optimized external stimulation and longitudinal recordings from Parkinsonian rats receiving closed-loop DBS. Our results demonstrate that STEER recovers interpretable update equations, predicts network adaptation under unseen stimulation schedules, and supports the design of improved intervention protocols. By elevating long-term plasticity from a hidden confound to an identifiable dynamical object, STEER provides a data-driven foundation for both mechanistic insight and principled optimization of brain stimulation.

Transformers have become increasingly popular in offline reinforcement learning (RL) due to their ability to treat agent trajectories as sequences, reframing policy learning as a sequence modeling task. However, in partially observable environments (POMDPs), effective decision-making depends on retaining information about past events - something that standard transformers struggle with due to the quadratic complexity of self-attention, which limits their context length. One solution to this problem is to extend transformers with memory mechanisms. We propose the Recurrent Action Transformer with Memory (RATE), a novel transformer-based architecture for offline RL that incorporates a recurrent memory mechanism designed to regulate information retention. We evaluate RATE across a diverse set of environments: memory-intensive tasks (ViZDoom-Two-Colors, T-Maze, Memory Maze, Minigrid-Memory, and POPGym), as well as standard Atari and MuJoCo benchmarks. Our comprehensive experiments demonstrate that RATE significantly improves performance in memory-dependent settings while remaining competitive on standard tasks across a broad range of baselines. These findings underscore the pivotal role of integrated memory mechanisms in offline RL and establish RATE as a unified, high-capacity architecture for effective decision-making over extended horizons.

Training recurrent neural networks (RNNs) with standard backpropagation through time (BPTT) can be challenging, especially in the presence of long input sequences. A practical alternative to reduce computational and memory overhead is to perform BPTT repeatedly over shorter segments of the training data set, corresponding to truncated BPTT. In this paper, we examine the training of RNNs when using such a truncated learning approach for time series tasks. Specifically, we establish theoretical bounds on the accuracy and performance loss when optimizing over subsequences instead of the full data sequence. This reveals that the burn-in phase of the RNN is an important tuning knob in its training, with significant impact on the performance guarantees. We validate our theoretical results through experiments on standard benchmarks from the fields of system identification and time series forecasting. In all experiments, we observe a strong influence of the burn-in phase on the training process, and proper tuning can lead to a reduction of the prediction error on the training and test data of more than 60% in some cases.

Continual learning (CL) has traditionally focused on minimizing exemplar memory, a constraint often misaligned with modern systems where GPU time, not storage, is the primary bottleneck. This paper challenges this paradigm by investigating a more realistic regime: one where memory is abundant enough to mitigate forgetting, but full retraining from scratch remains prohibitively expensive. In this practical "middle ground", we find that the core challenge shifts from stability to plasticity, as models become biased toward prior tasks and struggle to learn new ones. Conversely, improved stability allows simple replay baselines to outperform the state-of-the-art methods at a fraction of the GPU cost. To address this newly surfaced trade-off, we propose Weight Space Consolidation, a lightweight method that combines (1) rank-based parameter resets to restore plasticity with (2) weight averaging to enhance stability. Validated on both class-incremental learning with image classifiers and continual instruction tuning with large language models, our approach outperforms strong baselines while matching the low computational cost of replay, offering a scalable alternative to expensive full-retraining. These findings challenge long-standing CL assumptions and establish a new, cost-efficient baseline for real-world CL systems where exemplar memory is no longer the limiting factor.

We investigate the expressive power of state space models (SSM), which have recently emerged as a potential alternative to transformer architectures in large language models. Building on recent work, we analyse SSM expressiveness through fragments and extensions of linear temporal logic over finite traces. Our results show that the expressive capabilities of SSM vary substantially depending on the underlying gating mechanism. We further distinguish between SSM operating over fixed-width arithmetic (quantised models), whose expressive power remains within regular languages, and SSM with unbounded precision, which can capture counting properties and non-regular languages. In addition, we provide a systematic comparison between these different SSM variants and known results on transformers, thereby clarifying how the two architectures relate in terms of expressive power.

Accuracy-cost trade-offs are a fundamental aspect of scientific computing. Classical numerical methods inherently offer such a trade-off: increasing resolution, order, or precision typically yields more accurate solutions at higher computational cost. We introduce \textbf{Recurrent-Depth Simulator} (\textbf{RecurrSim}) an architecture-agnostic framework that enables explicit test-time control over accuracy-cost trade-offs in neural simulators without requiring retraining or architectural redesign. By setting the number of recurrent iterations $K$, users can generate fast, less-accurate simulations for exploratory runs or real-time control loops, or increase $K$ for more-accurate simulations in critical applications or offline studies. We demonstrate RecurrSim's effectiveness across fluid dynamics benchmarks (Burgers, Korteweg-De Vries, Kuramoto-Sivashinsky), achieving physically faithful simulations over long horizons even in low-compute settings. On high-dimensional 3D compressible Navier-Stokes simulations with 262k points, a 0.8B parameter RecurrFNO outperforms 1.6B parameter baselines while using 13.5\% less training memory. RecurrSim consistently delivers superior accuracy-cost trade-offs compared to alternative adaptive-compute models, including Deep Equilibrium and diffusion-based approaches. We further validate broad architectural compatibility: RecurrViT reduces error accumulation by 90\% compared to standard Vision Transformers on Active Matter, while RecurrUPT matches UPT performance on ShapeNet-Car using 44\% fewer parameters.

Dense associative memory, a fundamental instance of modern Hopfield networks, can store a large number of memory patterns as equilibrium states of recurrent networks. While the stationary-state storage capacity has been investigated, its dynamical properties have not yet been discussed. In this paper, we analyze the dynamics using an exact approach based on generating functional analysis. We show results on convergence properties of memory retrieval, such as the convergence time and the size of the attraction basins. Our analysis enables a quantitative evaluation of the convergence time and the storage capacity of dense associative memory, which is useful for model design. Unlike the traditional Hopfield model, the retrieval of a pattern does not act as additional noise to itself, suggesting that the structure of modern networks makes recall more robust. Furthermore, the methodology addressed here can be applied to other energy-based models, and thus has the potential to contribute to the design of future architectures.

This paper studies the problem of data-specific neural representations, aiming for compact, flexible, and modality-agnostic storage of individual visual data using neural networks. Our approach considers a visual datum as a set of discrete observations of an underlying continuous signal, thus requiring models capable of capturing the inherent structure of the signal. For this purpose, we investigate state-space models (SSMs), which are well-suited for modeling latent signal dynamics. We first explore the appealing properties of SSMs for data-specific neural representation and then present a novel framework that integrates SSMs into the representation pipeline. The proposed framework achieved compact representations and strong reconstruction performance across a range of visual data formats, suggesting the potential of SSMs for data-specific neural representations.

Discovering the neural mechanisms underpinning cognition is one of the grand challenges of neuroscience. Addressing this challenge greatly benefits from specific hypotheses about the underlying neural network dynamics. However, previous approaches bridging neural network dynamics and cognitive behaviour required iterative refinement of network architectures and/or objectives for normative task optimization, resulting in a long, and mostly heuristic, human-in-the-loop design process. Here, we offer an alternative approach that automates this process by explicitly training recurrent neural networks (RNNs) to reproduce behaviour, including the same characteristic errors, that humans and animals produce in a cognitive task. Achieving this required two main innovations. First, as the amount of behavioural data that can be collected in experiments is often too limited to suffice for training RNNs, we use a non-parametric generative model of behavioural responses to produce surrogate data for training RNNs. Second, to capture all relevant statistical moments in the data, rather than a limited number of hand-picked low-order moments as in previous moment matching-based approaches, we developed a novel diffusion model-based approach for training RNNs. We chose a visual working memory (VWM) task as our test-bed, as behaviour in this task is well known to produce response distributions that are patently multimodal (due to so-called swap errors). The resulting network dynamics correctly predicted previously reported qualitative features of neural data recorded in macaques. Importantly, this was only the case when RNNs were trained using our approach, fitting the full richness of behavioural data -- and not when only a limited set of behavioural signatures were fitted, nor when RNNs were trained for task optimality instead of reproducing behaviour (as has been typical for RNNs used to generate dynamical hypotheses). Our model also makes novel predictions about the mechanism of swap errors, which can be readily tested in experiments. These results suggest that fitting rich patterns of behaviour provides a powerful way for the automatic discovery of neural network dynamics supporting important cognitive functions.

State Space Models (SSMs), developed to tackle long sequence modeling tasks efficiently, offer both parallelizable training and fast inference. At their core are recurrent dynamical systems that maintain a hidden state, with update costs scaling with the state dimension. A key design challenge is striking the right balance between maximizing expressivity and limiting this computational burden. Control theory, and more specifically Hankel singular value analysis, provides a potent framework for the measure of energy for each state, as well as the balanced truncation of the original system down to a smaller representation with performance guarantees. Leveraging the eigenvalue stability properties of Hankel matrices, we apply this lens to SSMs during training, where only dimensions of high influence are identified and preserved. Our approach applies to Linear Time-Invariant SSMs such as Linear Recurrent Units, but is also extendable to selective models. Experiments show that in-training reduction significantly accelerates optimization while preserving expressivity, with compressed models retaining task-critical structure lost by models trained directly at smaller dimension. In other words, SSMs that begin large and shrink during training achieve computational efficiency while maintaining higher performance.

State space models (SSMs) often sacrifice capacity, search space, or stability to offset the memory and compute costs of large state dimensions. We introduce a structured post-training pruning method for SSMs — AIRE-Prune (Asymptotic Impulse- Response Energy for State PRUN(E)ing ) — that reduces each layer’s state dimension by directly minimizing long-run output-energy distortion. AIRE-Prune assigns every state a closed-form asymptotic impulse-response energy based score, i.e., the total impulse-response energy it contributes over an infinite horizon (time), and normalizes these scores layer-wise to enable global cross-layer comparison and selection. This extends modal truncation from single systems to deep stacks and aligns pruning with asymptotic response energy rather than worst-case gain. Across diverse sequence benchmarks, AIRE-Prune reveals substantial redundancy in SISO and MIMO SSMs with average pruning of 60.8%, with average accuracy drop of 0.29% without retraining while significantly lowering compute.