Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters

Large language models (LLMs) have revolutionized natural language processing and broadened their applicability across diverse commercial applications. However, the deployment of these models is constrained by high inference time in multilingual settings. To mitigate this challenge, this paper explores a training recipe of an assistant model in speculative decoding, which are leveraged to draft and-then its future tokens are verified by the target LLM. We show that language-specific draft models, optimized through a targeted pretrain-and-finetune strategy, substantially brings a speedup of inference time compared to the previous methods. We validate these models across various languages in inference time, out-of-domain speedup, and GPT-4o evaluation.

Block Transformer: Global-to-Local Language Modeling for Fast Inference

This paper presents the Block Transformer architecture which adopts hierarchical global-to-local modeling to autoregressive transformers to mitigate the inference bottlenecks of self-attention. To apply self-attention, the key-value (KV) cache of all previous sequences must be retrieved from memory at every decoding step. Thereby, this KV cache IO becomes a significant bottleneck in batch inference. We notice that these costs stem from applying self-attention on the global context, therefore we isolate the expensive bottlenecks of global modeling to lower layers and apply fast local modeling in upper layers. To mitigate the remaining costs in the lower layers, we aggregate input tokens into fixed size blocks and then apply self-attention at this coarse level. Context information is aggregated into a single embedding to enable upper layers to decode the next block of tokens, without global attention. Free of global attention bottlenecks, the upper layers can fully utilize the compute hardware to maximize inference throughput. By leveraging global and local modules, the Block Transformer architecture demonstrates 10-20x gains in inference throughput compared to vanilla transformers with equivalent perplexity. Our work introduces a new approach to optimize language model inference through novel application of global-to-local modeling. Code is available at https://github.com/itsnamgyu/block-transformer.

Towards Fast Inference: Exploring and Improving Blockwise Parallel Drafts

Despite the remarkable strides made by autoregressive language models, their potential is often hampered by the slow inference speeds inherent in sequential token generation. Blockwise parallel decoding (BPD) was proposed by Stern et al. (2018) as a way to improve inference speed of language models. In this paper, we make two contributions to understanding and improving BPD drafts. We first offer an analysis of the token distributions produced by the BPD prediction heads. Secondly, we use this analysis to inform algorithms to improve BPD inference speed by refining the BPD drafts using small n-gram or neural language models. We empirically show that these refined BPD drafts yield a higher average verified prefix length across tasks.

Semantic Layering in Room Segmentation via LLMs

In this paper, we introduce Semantic Layering in Room Segmentation via LLMs (SeLRoS), an advanced method for semantic room segmentation by integrating Large Language Models (LLMs) with traditional 2D map-based segmentation. Unlike previous approaches that solely focus on the geometric segmentation of indoor environments, our work enriches segmented maps with semantic data, including object identification and spatial relationships, to enhance robotic navigation. By leveraging LLMs, we provide a novel framework that interprets and organizes complex information about each segmented area, thereby improving the accuracy and contextual relevance of room segmentation. Furthermore, SeLRoS overcomes the limitations of existing algorithms by using a semantic evaluation method to accurately distinguish true room divisions from those erroneously generated by furniture and segmentation inaccuracies. The effectiveness of SeLRoS is verified through its application across 30 different 3D environments. Source code and experiment videos for this work are available at: https://sites.google.com/view/selros.

Non-linear Fusion in Federated Learning: A Hypernetwork Approach to Federated Domain Generalization

Federated Learning (FL) has emerged as a promising paradigm in which multiple clients collaboratively train a shared global model while preserving data privacy. To create a robust and practicable FL framework, it is crucial to extend its ability to generalize well to unseen domains - a problem referred to as federated Domain Generalization (FDG), being still under-explored. We propose an innovative federated algorithm, termed hFedF for hypernetwork-based Federated Fusion, designed to bridge the performance gap between generalization and personalization, capable of addressing various degrees of domain shift. Essentially, the hypernetwork supports a non-linear fusion of client models enabling a comprehensive understanding of the underlying data distribution. We encompass an extensive discussion and provide novel insights into the tradeoff between personalization and generalization in FL. The proposed algorithm outperforms strong benchmarks on three widely-used data sets for DG in an exceeding number of cases.

Revisiting Early-Learning Regularization When Federated Learning Meets Noisy Labels

In the evolving landscape of federated learning (FL), addressing label noise presents unique challenges due to the decentralized and diverse nature of data collection across clients. Traditional centralized learning approaches to mitigate label noise are constrained in FL by privacy concerns and the heterogeneity of client data. This paper revisits early-learning regularization, introducing an innovative strategy, Federated Label-mixture Regularization (FLR). FLR adeptly adapts to FL's complexities by generating new pseudo labels, blending local and global model predictions. This method not only enhances the accuracy of the global model in both i.i.d. and non-i.i.d. settings but also effectively counters the memorization of noisy labels. Demonstrating compatibility with existing label noise and FL techniques, FLR paves the way for improved generalization in FL environments fraught with label inaccuracies.

Leveraging Normalization Layer in Adapters With Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learning

Cross-domain few-shot learning presents a formidable challenge, as models must be trained on base classes and then tested on novel classes from various domains with only a few samples at hand. While prior approaches have primarily focused on parameter-efficient methods of using adapters, they often overlook two critical issues: shifts in batch statistics and noisy sample statistics arising from domain discrepancy variations. In this paper, we introduce a novel generic framework that leverages normalization layer in adapters with Progressive Learning and Adaptive Distillation (ProLAD), marking two principal contributions. First, our methodology utilizes two separate adapters: one devoid of a normalization layer, which is more effective for similar domains, and another embedded with a normalization layer, designed to leverage the batch statistics of the target domain, thus proving effective for dissimilar domains. Second, to address the pitfalls of noisy statistics, we deploy two strategies: a progressive training of the two adapters and an adaptive distillation technique derived from features determined by the model solely with the adapter devoid of a normalization layer. Through this adaptive distillation, our approach functions as a modulator, controlling the primary adapter for adaptation, based on each domain. Evaluations on standard cross-domain few-shot learning benchmarks confirm that our technique outperforms existing state-of-the-art methodologies.

Distort, Distract, Decode: Instruction-Tuned Model Can Refine its Response from Noisy Instructions

While instruction-tuned language models have demonstrated impressive zero-shot generalization, these models often struggle to generate accurate responses when faced with instructions that fall outside their training set. This paper presents Instructive Decoding (ID), a simple yet effective approach that augments the efficacy of instruction-tuned models. Specifically, ID adjusts the logits for next-token prediction in a contrastive manner, utilizing predictions generated from a manipulated version of the original instruction, referred to as a noisy instruction. This noisy instruction aims to elicit responses that could diverge from the intended instruction yet remain plausible. We conduct experiments across a spectrum of such noisy instructions, ranging from those that insert semantic noise via random words to others like 'opposite' that elicit the deviated responses. Our approach achieves considerable performance gains across various instruction-tuned models and tasks without necessitating any additional parameter updates. Notably, utilizing 'opposite' as the noisy instruction in ID, which exhibits the maximum divergence from the original instruction, consistently produces the most significant performance gains across multiple models and tasks.

Navigating Data Heterogeneity in Federated Learning A Semi-Supervised Approach for Object Detection

Federated Learning (FL) has emerged as a potent framework for training models across distributed data sources while maintaining data privacy. Nevertheless, it faces challenges with limited high-quality labels and non-IID client data, particularly in applications like autonomous driving. To address these hurdles, we navigate the uncharted waters of Semi-Supervised Federated Object Detection (SSFOD). We present a pioneering SSFOD framework, designed for scenarios where labeled data reside only at the server while clients possess unlabeled data. Notably, our method represents the inaugural implementation of SSFOD for clients with 0% labeled non-IID data, a stark contrast to previous studies that maintain some subset of labels at each client. We propose FedSTO, a two-stage strategy encompassing Selective Training followed by Orthogonally enhanced full-parameter training, to effectively address data shift (e.g. weather conditions) between server and clients. Our contributions include selectively refining the backbone of the detector to avert overfitting, orthogonality regularization to boost representation divergence, and local EMA-driven pseudo label assignment to yield high-quality pseudo labels. Extensive validation on prominent autonomous driving datasets (BDD100K, Cityscapes, and SODA10M) attests to the efficacy of our approach, demonstrating state-of-the-art results. Remarkably, FedSTO, using just 20-30% of labels, performs nearly as well as fully-supervised centralized training methods.

DynaCon: Dynamic Robot Planner with Contextual Awareness via LLMs

Mobile robots often rely on pre-existing maps for effective path planning and navigation. However, when these maps are unavailable, particularly in unfamiliar environments, a different approach become essential. This paper introduces DynaCon, a novel system designed to provide mobile robots with contextual awareness and dynamic adaptability during navigation, eliminating the reliance of traditional maps. DynaCon integrates real-time feedback with an object server, prompt engineering, and navigation modules. By harnessing the capabilities of Large Language Models (LLMs), DynaCon not only understands patterns within given numeric series but also excels at categorizing objects into matched spaces. This facilitates dynamic path planner imbued with contextual awareness. We validated the effectiveness of DynaCon through an experiment where a robot successfully navigated to its goal using reasoning. Source code and experiment videos for this work can be found at: https://sites.google.com/view/dynacon.