Multi-Agent Reinforcement Learning (MARL) presents a promising approach for addressing the complexity of Traffic Signal Control (TSC) in urban environments. However, existing platforms for MARL-based TSC research face challenges such as slow simulation speeds and convoluted, difficult-to-maintain codebases. To address these limitations, we introduce PyTSC, a robust and flexible simulation environment that facilitates the training and evaluation of MARL algorithms for TSC. PyTSC integrates multiple simulators, such as SUMO and CityFlow, and offers a streamlined API, empowering researchers to explore a broad spectrum of MARL approaches efficiently. PyTSC accelerates experimentation and provides new opportunities for advancing intelligent traffic management systems in real-world applications.
相關內容
The development of Large Language Models (LLMs) relies on extensive text corpora, which are often unevenly distributed across languages. This imbalance results in LLMs performing significantly better on high-resource languages like English, German, and French, while their capabilities in low-resource languages remain inadequate. Currently, there is a lack of quantitative methods to evaluate the performance of LLMs in these low-resource languages. To address this gap, we propose the Language Ranker, an intrinsic metric designed to benchmark and rank languages based on LLM performance using internal representations. By comparing the LLM's internal representation of various languages against a baseline derived from English, we can assess the model's multilingual capabilities in a robust and language-agnostic manner. Our analysis reveals that high-resource languages exhibit higher similarity scores with English, demonstrating superior performance, while low-resource languages show lower similarity scores, underscoring the effectiveness of our metric in assessing language-specific capabilities. Besides, the experiments show that there is a strong correlation between the LLM's performance in different languages and the proportion of those languages in its pre-training corpus. These insights underscore the efficacy of the Language Ranker as a tool for evaluating LLM performance across different languages, particularly those with limited resources.
Although fine-tuning Large Language Models (LLMs) with multilingual data can rapidly enhance the multilingual capabilities of LLMs, they still exhibit a performance gap between the dominant language (e.g., English) and non-dominant ones due to the imbalance of training data across languages. To further enhance the performance of non-dominant languages, we propose ShifCon, a Shift-based Contrastive framework that aligns the internal forward process of other languages toward that of the dominant one. Specifically, it shifts the representations of non-dominant languages into the dominant language subspace, allowing them to access relatively rich information encoded in the model parameters. The enriched representations are then shifted back into their original language subspace before generation. Moreover, we introduce a subspace distance metric to pinpoint the optimal layer area for shifting representations and employ multilingual contrastive learning to further enhance the alignment of representations within this area. Experiments demonstrate that our ShifCon framework significantly enhances the performance of non-dominant languages, particularly for low-resource ones. Further analysis offers extra insights to verify the effectiveness of ShifCon and propel future research
Large Multimodal Models (LMMs) have demonstrated exceptional comprehension and interpretation capabilities in Autonomous Driving (AD) by incorporating large language models. Despite the advancements, current data-driven AD approaches tend to concentrate on a single dataset and specific tasks, neglecting their overall capabilities and ability to generalize. To bridge these gaps, we propose DriveMM, a general large multimodal model designed to process diverse data inputs, such as images and multi-view videos, while performing a broad spectrum of AD tasks, including perception, prediction, and planning. Initially, the model undergoes curriculum pre-training to process varied visual signals and perform basic visual comprehension and perception tasks. Subsequently, we augment and standardize various AD-related datasets to fine-tune the model, resulting in an all-in-one LMM for autonomous driving. To assess the general capabilities and generalization ability, we conduct evaluations on six public benchmarks and undertake zero-shot transfer on an unseen dataset, where DriveMM achieves state-of-the-art performance across all tasks. We hope DriveMM as a promising solution for future end-toend autonomous driving applications in the real world.
This manuscript introduces the hype-adjusted probability measure developed in the context of a new Natural Language Processing (NLP) approach for market forecasting. A novel sentiment score equation is presented to capture component and memory effects and assign dynamic parameters, enhancing the impact of intraday news data on forecasting next-period volatility for selected U.S. semiconductor stocks. This approach integrates machine learning techniques to analyze and improve the predictive value of news. Building on the research of Geman's, this work improves forecast accuracy by assigning specific weights to each component of news sources and individual stocks in the portfolio, evaluating time-memory effects on market reactions, and incorporating shifts in sentiment direction. Finally, we propose the Hype-Adjusted Probability Measure, proving its existence and uniqueness, and discuss its theoretical applications in finance for NLP-based volatility forecasting, outlining future research pathways inspired by its concepts.
We introduce SAM4MLLM, an innovative approach which integrates the Segment Anything Model (SAM) with Multi-Modal Large Language Models (MLLMs) for pixel-aware tasks. Our method enables MLLMs to learn pixel-level location information without requiring excessive modifications to the existing model architecture or adding specialized tokens. We introduce an inquiry-based approach that can effectively find prompt points for SAM to perform segmentation based on MLLM. It combines detailed visual information with the powerful expressive capabilities of large language models in a unified language-based manner without additional computational overhead in learning. Experimental results on pubic benchmarks demonstrate the effectiveness of our approach.
Recent studies have proposed integrating Chain-of-Thought (CoT) reasoning to further enhance the reliability of Code Language Models (CLMs) in generating code, a step-by-step approach that breaks down complex programming tasks into manageable sub-problems. Advances in this area have introduced CoT models, specifically designed to integrate CoT reasoning effectively into language models, achieving notable improvements in code generation. Despite these advancements, the security of CoT models has not been systematically studied. In this study, we aim to fill this gap by investigating the vulnerability of CoT models to backdoor injection in code generation tasks. To address this, we propose a model-agnostic backdoor attack method SABER (\textbf{S}elf-\textbf{A}ttention-\textbf{B}as\textbf{E}d backdoo\textbf{R}) based on the self-attention mechanism. SABER begins by selecting a malicious output as the backdoor using code mutation operations. It then identifies tokens most relevant to poisoned content by analyzing self-attention scores in the CodeBERT model. Finally, it applies semantic-preserving perturbations to generate adaptive and natural triggers. Our experiments on HumanEval-CoT and OpenEval-CoT test sets demonstrate that CoT models are susceptible to backdoor attacks via data poisoning. Taking the OpenEval-CoT dataset as an example, SABER achieves an ASR of 76.19%, representing an improvement of 14.29% over RIPPLe and a substantial 23.08% enhancement compared to BadPre. Further evaluations using ONION for automated detection and human studies reveal that SABER is stealthier and harder to detect, bypassing 77.27% of automated detection, with a human detection rate of just 3.17%. Our findings reveal that backdoors can be injected into CoT models to manipulate downstream code generation tasks.
The primary challenge in Video Object Detection (VOD) is effectively exploiting temporal information to enhance object representations. Traditional strategies, such as aggregating region proposals, often suffer from feature variance due to the inclusion of background information. We introduce a novel instance mask-based feature aggregation approach, significantly refining this process and deepening the understanding of object dynamics across video frames. We present FAIM, a new VOD method that enhances temporal Feature Aggregation by leveraging Instance Mask features. In particular, we propose the lightweight Instance Feature Extraction Module (IFEM) to learn instance mask features and the Temporal Instance Classification Aggregation Module (TICAM) to aggregate instance mask and classification features across video frames. Using YOLOX as a base detector, FAIM achieves 87.9% mAP on the ImageNet VID dataset at 33 FPS on a single 2080Ti GPU, setting a new benchmark for the speed-accuracy trade-off. Additional experiments on multiple datasets validate that our approach is robust, method-agnostic, and effective in multi-object tracking, demonstrating its broader applicability to video understanding tasks.
The fluid antenna (FA)-enabled multiple-input multiple-output (MIMO) system based on index modulation (IM), referred to as FA-IM, significantly enhances spectral efficiency (SE) compared to the conventional FA-assisted MIMO system. This paper proposes an innovative FA grouping-based IM (FAG-IM) system to improve performance in mitigating the high spatial correlation between multiple activated ports. A block grouping scheme is employed based on the spatial correlation model and the distribution structure of the ports. Then, a closed-form expression for the average bit error probability (ABEP) upper bound of the FAG-IM system is derived. In order to reduce the receiver complexity of the proposed system, the message passing mechanism is first incorporated into the FAG-IM system. Subsequently, within the approximate message passing (AMP) framework, an efficient structured AMP (S-AMP) detector is devised by leveraging the structural characteristics of the transmission signal vector. Simulation results confirm that the proposed FAG-IM system significantly outperforms the existing FA-IM system in the presence of spatial correlation. The derived ABEP curve aligns well with the numerical results, providing an efficient theoretical tool for evaluating the system performance. Additionally, simulation results demonstrate that the proposed low-complexity S-AMP detector not only reduces the time complexity to a linear scale but also substantially improves bit error rate (BER) performance compared to the minimum mean square error (MMSE) detector, thus facilitating the practical implementation of the FAG-IM system.
The quadratic computational complexity of the attention mechanism in current Large Language Models (LLMs) renders inference with long contexts prohibitively expensive. To address this challenge, various approaches aim to retain critical portions of the context to optimally approximate Full Attention (FA) through Key-Value (KV) compression or Sparse Attention (SA), enabling the processing of virtually unlimited text lengths in a streaming manner. However, these methods struggle to achieve performance levels comparable to FA, particularly in retrieval tasks. In this paper, our analysis of attention head patterns reveals that LLMs' attention distributions show strong local correlations, naturally reflecting a chunking mechanism for input context. We propose Ltri-LLM framework, which divides KVs into spans, stores them in an offline index, and retrieves the relevant KVs into memory for various queries. Experimental results on popular long text benchmarks show that Ltri-LLM can achieve performance close to FA while maintaining efficient, streaming-based inference.
The documentation of the Neo-Aramaic dialects before their extinction has been described as the most urgent task in all of Semitology today. The death of this language will be an unfathomable loss to the descendents of the indigenous speakers of Aramaic, now predominantly diasporic after forced displacement due to violence. This paper develops an ASR model to expedite the documentation of this endangered language and generalizes the strategy in a new framework we call NoLoR.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191