Jiale Chen

Jiale Chen, Dingling Yao, Adeel Pervez et al.

We propose Scalable Mechanistic Neural Network (S-MNN), an enhanced neural network framework designed for scientific machine learning applications involving long temporal sequences. By reformulating the original Mechanistic Neural Network (MNN) (Pervez et al., 2024), we reduce the computational time and space complexities from cubic and quadratic with respect to the sequence length, respectively, to linear. This significant improvement enables efficient modeling of long-term dynamics without sacrificing accuracy or interpretability. Extensive experiments demonstrate that S-MNN matches the original MNN in precision while substantially reducing computational resources. Consequently, S-MNN can drop-in replace the original MNN in applications, providing a practical and efficient tool for integrating mechanistic bottlenecks into neural network models of complex dynamical systems. Source code is available at https://github.com/IST-DASLab/ScalableMNN.

Elias Frantar, Roberto L. Castro, Jiale Chen et al.

As inference on Large Language Models (LLMs) emerges as an important workload in machine learning applications, weight quantization has become a standard technique for efficient GPU deployment. Quantization not only reduces model size, but has also been shown to yield substantial speedups for single-user inference, due to reduced memory movement, with low accuracy impact. Yet, it remains open whether speedups are achievable also in \emph{batched} settings with multiple parallel clients, which are highly relevant for practical serving. It is unclear whether GPU kernels can be designed to remain practically memory-bound, while supporting the substantially increased compute requirements of batched workloads. This paper resolves this question positively by describing the design of Mixed-precision Auto-Regressive LINear kernels, called MARLIN. Concretely, given a model whose weights are compressed via quantization to, e.g., 4 bits per element, MARLIN shows that batchsizes up to 16-32 can be supported with close to maximum ($4\times$) quantization speedup, and larger batchsizes up to 64-128 with gradually decreasing, but still significant, acceleration. MARLIN accomplishes this via a combination of techniques, such as asynchronous memory access, complex task scheduling and pipelining, and bespoke quantization support. Our experiments show that MARLIN's near-optimal performance on individual LLM layers across different scenarios can also lead to end-to-end LLM inference speedups (of up to $2.8\times$) when integrated with the popular vLLM serving engine. Finally, MARLIN is extensible to further compression techniques, like NVIDIA 2:4 sparsity, leading to additional speedups.

Andrei Panferov, Jiale Chen, Soroush Tabesh et al.

One approach to reducing the massive costs of large language models (LLMs) is the use of quantized or sparse representations for training or deployment. While post-training compression methods are very popular, the question of obtaining even more accurate compressed models by directly training over such representations, i.e., Quantization-Aware Training (QAT), is still open: for example, a recent study (arXiv:2411.04330) put the "optimal" bit-width at which models can be trained using QAT, while staying accuracy-competitive with standard FP16/BF16 precision, at 8-bits weights and activations. We advance this state-of-the-art via a new method called QuEST, for which we demonstrate optimality at 4-bits and stable convergence as low as 1-bit weights and activations. QuEST achieves this by improving two key aspects of QAT methods: (1) accurate and fast quantization of the (continuous) distributions of weights and activations via Hadamard normalization and MSE-optimal fitting; (2) a new trust gradient estimator based on the idea of explicitly minimizing the error between the noisy gradient computed over quantized states and the "true" (but unknown) full-precision gradient. Experiments on Llama-type architectures show that QuEST induces stable scaling laws across the entire range of hardware-supported precisions, and can be extended to sparse representations. We provide GPU kernel support showing that models produced by QuEST can be executed efficiently. Our code is available at https://github.com/IST-DASLab/QuEST.

Roberto L. Castro, Andrei Panferov, Soroush Tabesh et al.

Training large language models (LLMs) models directly in low-precision offers a way to address computational costs by improving both throughput and energy efficiency. For those purposes, NVIDIA's recent Blackwell architecture facilitates very low-precision operations using FP4 variants. Yet, current algorithms for training LLMs in FP4 precision face significant accuracy degradation and often rely on mixed-precision fallbacks. In this paper, we investigate hardware-supported FP4 training and introduce a new approach for accurate, end-to-end FP4 training with all the major computations (i.e., linear layers) in low precision. Through extensive evaluations on Llama-type models, we reveal a new low-precision scaling law that quantifies performance trade-offs across bit-widths and training setups. Guided by this investigation, we design an "optimal" technique in terms of accuracy-vs-computation, called Quartet. We implement Quartet using optimized CUDA kernels tailored for Blackwell, demonstrating that fully FP4-based training is a competitive alternative to FP16 half-precision and to FP8 training. Our code is available at https://github.com/IST-DASLab/Quartet.

Haoyu Wang, Guangyan Zhang, Jiale Chen et al.

With the development of speech large language models (speech LLMs), users can now interact directly with assistants via speech. However, most existing models only convert response content into speech without fully capturing the rich emotional cues in user queries, where the same sentence may convey different meanings depending on the expression. Emotional understanding is thus essential for improving human-machine interaction. Most empathetic speech LLMs rely on massive datasets, demanding high computational cost. A key challenge is to build models that generate empathetic responses with limited data and without large-scale training. To this end, we propose Emotion Omni, a model that understands emotional content in user speech and generates empathetic responses. We further developed a data pipeline to construct a 200k emotional dialogue dataset supporting empathetic speech assistants. Experiments show that Emotion Omni achieves comparable instruction-following ability without large-scale pretraining, while surpassing existing models in speech quality (UTMOS:4.41) and empathy (Emotion GPT Score: 3.97). These results confirm its improvements in both speech fidelity and emotional expressiveness. Demos are available at https://w311411.github.io/omni_demo/.

Zilin Zhao, Chishui Chen, Haotian Shi et al.

Efficient path planning for unmanned aerial vehicles (UAVs) is crucial in remote sensing and information collection. As task scales expand, the cooperative deployment of multiple UAVs significantly improves information collection efficiency. However, collaborative communication and decision-making for multiple UAVs remain major challenges in path planning, especially in noisy environments. To efficiently accomplish complex information collection tasks in 3D space and address robust communication issues, we propose a multi-agent reinforcement learning (MARL) framework for UAV path planning based on the Counterfactual Multi-Agent Policy Gradients (COMA) algorithm. The framework incorporates attention mechanism-based UAV communication protocol and training-deployment system, significantly improving communication robustness and individual decision-making capabilities in noisy conditions. Experiments conducted on both synthetic and real-world datasets demonstrate that our method outperforms existing algorithms in terms of path planning efficiency and robustness, especially in noisy environments, achieving a 78\% improvement in entropy reduction.

Xu Tan, Yichong Leng, Jiale Chen et al.

Multilingual neural machine translation (NMT) has recently been investigated from different aspects (e.g., pivot translation, zero-shot translation, fine-tuning, or training from scratch) and in different settings (e.g., rich resource and low resource, one-to-many, and many-to-one translation). This paper concentrates on a deep understanding of multilingual NMT and conducts a comprehensive study on a multilingual dataset with more than 20 languages. Our results show that (1) low-resource language pairs benefit much from multilingual training, while rich-resource language pairs may get hurt under limited model capacity and training with similar languages benefits more than dissimilar languages; (2) fine-tuning performs better than training from scratch in the one-to-many setting while training from scratch performs better in the many-to-one setting; (3) the bottom layers of the encoder and top layers of the decoder capture more language-specific information, and just fine-tuning these parts can achieve good accuracy for low-resource language pairs; (4) direct translation is better than pivot translation when the source language is similar to the target language (e.g., in the same language branch), even when the size of direct training data is much smaller; (5) given a fixed training data budget, it is better to introduce more languages into multilingual training for zero-shot translation.

Xu Tan, Jiale Chen, Di He et al.

Multilingual neural machine translation (NMT), which translates multiple languages using a single model, is of great practical importance due to its advantages in simplifying the training process, reducing online maintenance costs, and enhancing low-resource and zero-shot translation. Given there are thousands of languages in the world and some of them are very different, it is extremely burdensome to handle them all in a single model or use a separate model for each language pair. Therefore, given a fixed resource budget, e.g., the number of models, how to determine which languages should be supported by one model is critical to multilingual NMT, which, unfortunately, has been ignored by previous work. In this work, we develop a framework that clusters languages into different groups and trains one multilingual model for each cluster. We study two methods for language clustering: (1) using prior knowledge, where we cluster languages according to language family, and (2) using language embedding, in which we represent each language by an embedding vector and cluster them in the embedding space. In particular, we obtain the embedding vectors of all the languages by training a universal neural machine translation model. Our experiments on 23 languages show that the first clustering method is simple and easy to understand but leading to suboptimal translation accuracy, while the second method sufficiently captures the relationship among languages well and improves the translation accuracy for almost all the languages over baseline methods

Tianyu He, Jiale Chen, Xu Tan et al.

Neural machine translation on low-resource language is challenging due to the lack of bilingual sentence pairs. Previous works usually solve the low-resource translation problem with knowledge transfer in a multilingual setting. In this paper, we propose the concept of Language Graph and further design a novel graph distillation algorithm that boosts the accuracy of low-resource translations in the graph with forward and backward knowledge distillation. Preliminary experiments on the TED talks multilingual dataset demonstrate the effectiveness of our proposed method. Specifically, we improve the low-resource translation pair by more than 3.13 points in terms of BLEU score.

Zhizheng Zhang, Jiale Chen, Zhibo Chen et al.

Deep Deterministic Policy Gradient (DDPG) has been proved to be a successful reinforcement learning (RL) algorithm for continuous control tasks. However, DDPG still suffers from data insufficiency and training inefficiency, especially in computationally complex environments. In this paper, we propose Asynchronous Episodic DDPG (AE-DDPG), as an expansion of DDPG, which can achieve more effective learning with less training time required. First, we design a modified scheme for data collection in an asynchronous fashion. Generally, for asynchronous RL algorithms, sample efficiency or/and training stability diminish as the degree of parallelism increases. We consider this problem from the perspectives of both data generation and data utilization. In detail, we re-design experience replay by introducing the idea of episodic control so that the agent can latch on good trajectories rapidly. In addition, we also inject a new type of noise in action space to enrich the exploration behaviors. Experiments demonstrate that our AE-DDPG achieves higher rewards and requires less time consuming than most popular RL algorithms in Learning to Run task which has a computationally complex environment. Not limited to the control tasks in computationally complex environments, AE-DDPG also achieves higher rewards and 2- to 4-fold improvement in sample efficiency on average compared to other variants of DDPG in MuJoCo environments. Furthermore, we verify the effectiveness of each proposed technique component through abundant ablation study.