Related papers: RevoNAD: Reflective Evolutionary Exploration for N…

Self-Refinement refers to a model's ability to revise its own responses to produce improved outputs. This capability can also serve as a fundamental mechanism for Self-Improvement, for example, by reconstructing datasets with refined…

Large language models (LLMs) have been increasingly used to interact with external environments (e.g., games, compilers, APIs) as goal-driven agents. However, it remains challenging for these language agents to quickly and efficiently learn…

With rapid advances in code generation, reasoning, and problem-solving, Large Language Models (LLMs) are increasingly applied in robotics. Most existing work focuses on high-level tasks such as task decomposition. A few studies have…

Understanding large-scale, complex software systems is a major challenge for developers, who spend a significant portion of their time on program comprehension. Traditional tools such as static visualizations and reverse engineering…

The rapidly evolving field of Artificial Intelligence necessitates automated approaches to co-design neural network architecture and neural accelerators to maximize system efficiency and address productivity challenges. To enable joint…

Large language models (LLMs) have improved Verilog generation from natural-language specifications, but most pipelines still treat generation as isolated sampling followed by functional checking. This is insufficient for practical RTL…

Autoprompting is the process of automatically selecting optimized prompts for language models, which has been gaining popularity with the rapid advancement of prompt engineering, driven by extensive research in the field of large language…

Neural Architecture Search (NAS) has been widely studied for designing discriminative deep learning models such as image classification, object detection, and semantic segmentation. As a large number of priors have been obtained through the…

Reinforcement Learning (RL) has shown promise in improving the reasoning abilities of Large Language Models (LLMs). However, the specific challenges of adapting RL to multimodal data and formats remain relatively unexplored. In this work,…

Vision-language models (VLMs) have demonstrated remarkable capabilities in robotic planning, particularly for long-horizon tasks that require a holistic understanding of the environment for task decomposition. Existing methods typically…

Multimodal Large Language Models (MLLMs) have achieved remarkable success, yet they remain prone to perception-related hallucinations in fine-grained tasks. This vulnerability arises from a fundamental limitation: their reasoning is largely…

Current LLM-based driving agents that rely on unstructured plain-text memory suffer from low-precision scene retrieval and inefficient reflection. To address this limitation, we present RESPOND, a structured decision-making framework for…

Large Language Models (LLMs) excel across diverse domains but suffer from high energy costs due to quadratic attention and dense Feed-Forward Network (FFN) operations. To address these issues, we propose Module-aware Architecture Refinement…

Large language models (LLMs) are increasingly used as generators in iterative neural architecture search (NAS), yet no formal convergence theory exists for this class of algorithms. We model iterative LLM-NAS as a parametric Cross-Entropy…

Spiking Neural Networks (SNNs) have received considerable attention not only for their superiority in energy efficiency with discrete signal processing but also for their natural suitability to integrate multi-scale biological plasticity.…

When employing an evolutionary algorithm to optimize a neural networks architecture, developers face the added challenge of tuning the evolutionary algorithm's own hyperparameters - population size, mutation rate, cloning rate, and number…

Reinforcement learning (RL) can refine the reasoning abilities of large language models (LLMs), but critically depends on a key prerequisite: the LLM can already generate high-utility reasoning paths with non-negligible probability. For…

To achieve excellent performance with modern neural networks, having the right network architecture is important. Neural Architecture Search (NAS) concerns the automatic discovery of task-specific network architectures. Modern NAS…

The advancement of embodied intelligence is accelerating the integration of robots into daily life as human assistants. This evolution requires robots to not only interpret high-level instructions and plan tasks but also perceive and adapt…

Large language models (LLMs) with Chain-of-Thought (CoT) reasoning have achieved strong performance across diverse tasks, including mathematics, coding, and general reasoning. A distinctive ability of these reasoning models is…