Related papers: ChipSeek: Optimizing Verilog Generation via EDA-In…

While post-training compression techniques effectively reduce the memory footprint, latency, and power consumption of Large Language Models (LLMs), they often result in noticeable accuracy degradation and remain limited by hardware and…

Limitations in Large Language Model (LLM) capabilities for hardware design tasks, such as generating functional Verilog codes, have motivated various fine-tuning optimizations utilizing curated hardware datasets from open-source…

Post-training has become essential for adapting large language models (LLMs) to complex downstream behaviors, including instruction following, preference alignment, and multi-step reasoning. Reinforcement learning with verifiable rewards…

Large Language Models (LLMs) have made substantial strides in structured tasks through Reinforcement Learning (RL), demonstrating proficiency in mathematical reasoning and code generation. However, applying RL in broader domains like…

Reinforcement learning (RL) with unit test feedback has enhanced large language models' (LLMs) code generation, but relies on sparse rewards provided only after complete code evaluation, limiting learning efficiency and incremental…

We present four main contributions to enhance the performance of Large Language Models (LLMs) in generating domain-specific code: (i) utilizing LLM-based data splitting and data renovation techniques to improve the semantic representation…

Register Transfer Level (RTL) code optimization is crucial for enhancing the efficiency and performance of digital circuits during early synthesis stages. Currently, optimization relies heavily on manual efforts by skilled engineers, often…

Search agents powered by Large Language Models (LLMs) have demonstrated significant potential in tackling knowledge-intensive tasks. Reinforcement learning (RL) has emerged as a powerful paradigm for training these agents to perform…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective approach for improving the reasoning abilities of large language models (LLMs). The Group Relative Policy Optimization (GRPO) family has demonstrated strong…

Aiming to produce reinforcement learning (RL) policies that are human-interpretable and can generalize better to novel scenarios, Trivedi et al. (2021) present a method (LEAPS) that first learns a program embedding space to continuously…

Context: Due to the demand for strong algorithmic reasoning, complex logic implementation, and strict adherence to input/output formats and resource constraints, competitive programming generation by large language models (LLMs) is…

Large Language Models (LLMs) have excelled as high-level semantic planners for sequential decision-making tasks. However, harnessing them to learn complex low-level manipulation tasks, such as dexterous pen spinning, remains an open…

Continuous-time nonlinear optimal control problems hold great promise in real-world applications. After decades of development, reinforcement learning (RL) has achieved some of the greatest successes as a general nonlinear control design…

As large language models (LLMs) like ChatGPT exhibited unprecedented machine intelligence, it also shows great performance in assisting hardware engineers to realize higher-efficiency logic design via natural language interaction. To…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Recently, Large Language Models (LLMs) have rapidly evolved, approaching Artificial General Intelligence (AGI) while benefiting from large-scale reinforcement learning to enhance Human Alignment (HA) and Reasoning. Recent reward-based…

Achieving the effective design and improvement of reward functions in reinforcement learning (RL) tasks with complex custom environments and multiple requirements presents considerable challenges. In this paper, we propose ERFSL, an…

Deploying Large Language Model (LLM) applications, particularly those relying on Retrieval-Augmented Generation (RAG), remains challenging due to high computational demands, outdated knowledge bases, and the need to manually select optimal…

Recently, there has been a surging interest in using large language models (LLMs) for Verilog code generation. However, the existing approaches are limited in terms of the quality of the generated Verilog code. To address such limitations,…

Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing…