Related papers: Recursive Dynamics in Fast-Weights Homeostatic Ree…

Brain-like intelligent systems need brain-like learning methods. Equilibrium Propagation (EP) is a biologically plausible learning framework with strong potential for brain-inspired computing hardware. However, existing im-plementations of…

Processing sequential data of variable length is a major challenge in a wide range of applications, such as speech recognition, language modeling, generative image modeling and machine translation. Here, we address this challenge by…

We study the regret guarantee for risk-sensitive reinforcement learning (RSRL) via distributional reinforcement learning (DRL) methods. In particular, we consider finite episodic Markov decision processes whose objective is the entropic…

Reconfigurable intelligent surface (RIS)-empowered communication has emerged as a novel concept for customizing future wireless environments in a cost- and energy-efficient way. However, due to double path loss, existing fully passive RIS…

Reward models (RMs) are critical for aligning Large Language Models via Reinforcement Learning from Human Feedback (RLHF). While Generative Reward Models (GRMs) achieve superior accuracy through chain-of-thought (CoT) reasoning, they incur…

Reflexion-style agents rely on self-generated reflections as memory, implicitly assuming that agents can accurately diagnose their own failures.We show that this assumption can fail systematically: across ALFWorld and HumanEval, agents…

Self-reflection -- the ability of a large language model (LLM) to revisit, evaluate, and revise its own reasoning -- has recently emerged as a powerful behavior enabled by reinforcement learning with verifiable rewards (RLVR). While…

Standard reinforcement learning (RL) for large language model (LLM) agents typically optimizes extrinsic rewards, prioritizing isolated task completion over continual adaptation. Consequently, agents often converge to suboptimal policies…

Recursive learning -- where models are trained on data generated by previous versions of themselves -- is increasingly common in large language models, autonomous agents, and self-supervised systems. However, standard performance metrics…

Large-scale autoregressive models pretrained on next-token prediction and finetuned with reinforcement learning (RL) have achieved unprecedented success on many problem domains. During RL, these models explore by generating new outputs, one…

Recurrent neural network architectures can have useful computational properties, with complex temporal dynamics and input-sensitive attractor states. However, evaluation of recurrent dynamic architectures requires solution of systems of…

We introduce a computationally efficient and tunable feedback delay network (FDN) architecture for real-time room impulse response (RIR) rendering that addresses the computational and latency challenges inherent in traditional convolution…

Conventional deep networks rely on one-way backpropagation that overlooks reconciling high-level predictions with lower-level representations. We propose \emph{Contextual Feedback Loops} (CFLs), a lightweight mechanism that re-injects…

We present ReflexGrad, a dual-process architecture for within-episode failure recovery in LLM agents without demonstrations. When agents commit to a wrong approach early and exhaust the step budget, the post-failure trajectory contains the…

Current reasoning paradigms for LLMs include chain-of-thought, ReAct, and post-hoc self-critique. These paradigms rely on two assumptions that fail on long-horizon, multi-stage tasks. As a result, errors accumulate silently across reasoning…

Restoring critical loads after extreme events demands adaptive control to maintain distribution-grid resilience, yet uncertainty in renewable generation, limited dispatchable resources, and nonlinear dynamics make effective restoration…

Understanding how learning algorithms shape the computational strategies that emerge in neural networks remains a fundamental challenge in machine intelligence. While network architectures receive extensive attention, the role of the…

The passive and frequency-flat reflection of IRS, as well as the high-dimensional IRS-reflected channels, have posed significant challenges for efficient IRS channel estimation, especially in wideband communication systems with significant…

Recursive transformers reuse a shared weight block across multiple depth steps, trading parameters for compute. A core limitation: every step applies the same transformation, preventing the model from composing distinct operations across…

While biological vision systems rely heavily on feedback connections to iteratively refine perception, most artificial neural networks remain purely feedforward, processing input in a single static pass. In this work, we propose a…