相关论文: QeRL: Beyond Efficiency -- Quantization-enhanced R…

The rise of large language models (LLMs) has significantly advanced various natural language processing (NLP) tasks. However, the resource demands of these models pose substantial challenges. Structured pruning is an effective approach to…

MXFP4 arithmetic can dramatically accelerate reinforcement learning (RL) post-training of large language models (LLMs), yet the quantization error introduces severe accuracy degradation. Existing work treats the quantization error as a…

Parameter quantization for Large Language Models (LLMs) has attracted increasing attentions recently in reducing memory costs and improving computational efficiency. Early approaches have been widely adopted. However, the existing methods…

Traditional post-training quantization (PTQ) is considered an effective approach to reduce model size and accelerate inference of large-scale language models (LLMs). However, existing low-rank PTQ methods require costly fine-tuning to…

Post-training quantization (PTQ) has emerged as a promising technique to reduce the cost of large language models (LLMs). Specifically, PTQ can effectively mitigate memory consumption and reduce computational overhead in LLMs. To meet the…

Neural Radiance Field (NeRF) has emerged as a promising 3D reconstruction method, delivering high-quality results for AR/VR applications. While quantization methods and hardware accelerators have been proposed to enhance NeRF's…

The high inference demands of transformer-based Large Language Models (LLMs) pose substantial challenges in their deployment. To this end, we introduce Neural Block Linearization (NBL), a novel framework for accelerating transformer model…

Quantization has emerged as a promising technique for improving the memory and computational efficiency of large language models (LLMs). Though the trade-off between performance and efficiency is well-known, there is still much to be…

Large Language Models (LLMs) are increasingly being deployed on edge devices for long-context settings, creating a growing need for fast and efficient long-context inference. In these scenarios, the Key-Value (KV) cache is the primary…

The LoRA-finetuning quantization of LLMs has been extensively studied to obtain accurate yet compact LLMs for deployment on resource-constrained hardware. However, existing methods cause the quantized LLM to severely degrade and even fail…

We introduce ToRL (Tool-Integrated Reinforcement Learning), a framework for training large language models (LLMs) to autonomously use computational tools via reinforcement learning. Unlike supervised fine-tuning, ToRL allows models to…

Reinforcement Learning (RL) trains agents to learn optimal behavior by maximizing reward signals from experience datasets. However, RL training often faces memory limitations, leading to execution latencies and prolonged training times. To…

Fine-tuning pre-trained diffusion models under limited budgets has gained great success. In particular, the recent advances that directly fine-tune the quantized weights using Low-rank Adaptation (LoRA) further reduces training costs.…

Deep reinforcement learning (DRL) is one of the most powerful tools for synthesizing complex robotic behaviors. But training DRL models is incredibly compute and memory intensive, requiring large training datasets and replay buffers to…

The rapid progress of large language models (LLMs) has transformed natural language processing, yet the challenge of efficient adaptation remains unresolved. Full fine-tuning achieves strong performance but imposes prohibitive computational…

Large Language Models (LLMs) increasingly rely on reinforcement learning with verifiable rewards (RLVR) to elicit reliable chain-of-thought reasoning. However, the training process remains bottlenecked by the computationally expensive…

Integrating audio comprehension and generation into large language models (LLMs) remains challenging due to the continuous nature of audio and the resulting high sampling rates. Here, we introduce a novel approach that combines Variational…

LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference. Quantization is a…

The Newton-Raphson (NR) method is widely used for solving power flow (PF) equations due to its quadratic convergence. However, its performance deteriorates under poor initialization or extreme operating scenarios, e.g., high levels of…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks. However, their extensive memory requirements, particularly due to KV cache growth during long-text understanding and…