Improving Acoustic Scene Classification in Low-Resource Conditions

Acoustic Scene Classification (ASC) identifies an environment based on an audio signal. This paper explores ASC in low-resource conditions and proposes a novel model, DS-FlexiNet, which combines depthwise separable convolutions from MobileNetV2 with ResNet-inspired residual connections for a balance of efficiency and accuracy. To address hardware limitations and device heterogeneity, DS-FlexiNet employs Quantization Aware Training (QAT) for model compression and data augmentation methods like Auto Device Impulse Response (ADIR) and Freq-MixStyle (FMS) to improve cross-device generalization. Knowledge Distillation (KD) from twelve teacher models further enhances performance on unseen devices. The architecture includes a custom Residual Normalization layer to handle domain differences across devices, and depthwise separable convolutions reduce computational overhead without sacrificing feature representation. Experimental results show that DS-FlexiNet excels in both adaptability and performance under resource-constrained conditions.

GUI Testing Arena: A Unified Benchmark for Advancing Autonomous GUI Testing Agent

Nowadays, research on GUI agents is a hot topic in the AI community. However, current research focuses on GUI task automation, limiting the scope of applications in various GUI scenarios. In this paper, we propose a formalized and comprehensive environment to evaluate the entire process of automated GUI Testing (GTArena), offering a fair, standardized environment for consistent operation of diverse multimodal large language models. We divide the testing process into three key subtasks: test intention generation, test task execution, and GUI defect detection, and construct a benchmark dataset based on these to conduct a comprehensive evaluation. It evaluates the performance of different models using three data types: real mobile applications, mobile applications with artificially injected defects, and synthetic data, thoroughly assessing their capabilities in this relevant task. Additionally, we propose a method that helps researchers explore the correlation between the performance of multimodal language large models in specific scenarios and their general capabilities in standard benchmark tests. Experimental results indicate that even the most advanced models struggle to perform well across all sub-tasks of automated GUI Testing, highlighting a significant gap between the current capabilities of Autonomous GUI Testing and its practical, real-world applicability. This gap provides guidance for the future direction of GUI Agent development. Our code is available at https://github.com/ZJU-ACES-ISE/ChatUITest.

UAV-Enabled Passive 6D Movable Antennas: Joint Deployment and Beamforming Optimization

Intelligent reflecting surface (IRS) is composed of numerous passive reflecting elements and can be mounted on unmanned aerial vehicles (UAVs) to achieve six-dimensional (6D) movement by adjusting the UAV's three-dimensional (3D) location and 3D orientation simultaneously. Hence, in this paper, we investigate a new UAV-enabled passive 6D movable antenna (6DMA) architecture by mounting an IRS on a UAV and address the associated joint deployment and beamforming optimization problem. In particular, we consider a passive 6DMA-aided multicast system with a multi-antenna base station (BS) and multiple remote users, aiming to jointly optimize the IRS's location and 3D orientation, as well as its passive beamforming to maximize the minimum received signal-to-noise ratio (SNR) among all users under the practical angle-dependent signal reflection model. However, this optimization problem is challenging to be optimally solved due to the intricate relationship between the users' SNRs and the IRS's location and orientation. To tackle this challenge, we first focus on a simplified case with a single user, showing that one-dimensional (1D) orientation suffices to achieve the optimal performance. Next, we show that for any given IRS's location, the optimal 1D orientation can be derived in closed form, based on which several useful insights are drawn. To solve the max-min SNR problem in the general multi-user case, we propose an alternating optimization (AO) algorithm by alternately optimizing the IRS's beamforming and location/orientation via successive convex approximation (SCA) and hybrid coarse- and fine-grained search, respectively. To avoid undesirable local sub-optimal solutions, a Gibbs sampling (GS) method is proposed to generate new IRS locations and orientations for exploration in each AO iteration. Numerical results validate our theoretical analyses.

Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity

The increasing context window size in Large Language Models (LLMs), such as the GPT and LLaMA series, has improved their ability to tackle complex, long-text tasks, but at the cost of inference efficiency, particularly regarding memory and computational complexity. Existing methods, including selective token retention and window-based attention, improve efficiency but risk discarding important tokens needed for future text generation. In this paper, we propose an approach that enhances LLM efficiency without token loss by reducing the memory and computational load of less important tokens, rather than discarding them.We address two challenges: 1) investigating the distribution of important tokens in the context, discovering recent tokens are more important than distant tokens in context, and 2) optimizing resources for distant tokens by sharing attention scores across layers. The experiments show that our method saves $35\%$ KV cache without compromising the performance.

Track Any Peppers: Weakly Supervised Sweet Pepper Tracking Using VLMs

In the Detection and Multi-Object Tracking of Sweet Peppers Challenge, we present Track Any Peppers (TAP) - a weakly supervised ensemble technique for sweet peppers tracking. TAP leverages the zero-shot detection capabilities of vision-language foundation models like Grounding DINO to automatically generate pseudo-labels for sweet peppers in video sequences with minimal human intervention. These pseudo-labels, refined when necessary, are used to train a YOLOv8 segmentation network. To enhance detection accuracy under challenging conditions, we incorporate pre-processing techniques such as relighting adjustments and apply depth-based filtering during post-inference. For object tracking, we integrate the Matching by Segment Anything (MASA) adapter with the BoT-SORT algorithm. Our approach achieves a HOTA score of 80.4%, MOTA of 66.1%, Recall of 74.0%, and Precision of 90.7%, demonstrating effective tracking of sweet peppers without extensive manual effort. This work highlights the potential of foundation models for efficient and accurate object detection and tracking in agricultural settings.

What Factors Affect Multi-Modal In-Context Learning? An In-Depth Exploration

Recently, rapid advancements in Multi-Modal In-Context Learning (MM-ICL) have achieved notable success, which is capable of achieving superior performance across various tasks without requiring additional parameter tuning. However, the underlying rules for the effectiveness of MM-ICL remain under-explored. To fill this gap, this work aims to investigate the research question: "What factors affect the performance of MM-ICL?'' To this end, we investigate extensive experiments on the three core steps of MM-ICL including demonstration retrieval, demonstration ordering, and prompt construction using 6 vision large language models and 20 strategies. Our findings highlight (1) the necessity of a multi-modal retriever for demonstration retrieval, (2) the importance of intra-demonstration ordering over inter-demonstration ordering, and (3) the enhancement of task comprehension through introductory instructions in prompts. We hope this study can serve as a foundational guide for optimizing MM-ICL strategies in future research.

KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing

The development of large language models (LLMs) has significantly expanded model sizes, resulting in substantial GPU memory requirements during inference. The key and value storage of the attention map in the KV (key-value) cache accounts for more than 80\% of this memory consumption. Nowadays, most existing KV cache compression methods focus on intra-layer compression within a single Transformer layer but few works consider layer-wise compression. In this paper, we propose a plug-and-play method called \textit{KVSharer}, which shares the KV cache between layers to achieve layer-wise compression. Rather than intuitively sharing based on higher similarity, we discover a counterintuitive phenomenon: sharing dissimilar KV caches better preserves the model performance. Experiments show that \textit{KVSharer} can reduce KV cache computation by 30\%, thereby lowering memory consumption without significantly impacting model performance and it can also achieve at least 1.3 times generation acceleration. Additionally, we verify that \textit{KVSharer} is compatible with existing intra-layer KV cache compression methods, and combining both can further save memory.

Codebook Design and Performance Analysis for Wideband Beamforming in Terahertz Communications

The codebook-based analog beamforming is appealing for future terahertz (THz) communications since it can generate high-gain directional beams with low-cost phase shifters via low-complexity beam training. However, conventional beamforming codebook design based on array response vectors for narrowband communications may suffer from severe performance loss in wideband systems due to the ``beam squint" effect over frequency. To tackle this issue, we propose in this paper a new codebook design method for analog beamforming in wideband THz systems. In particular, to characterize the analog beamforming performance in wideband systems, we propose a new metric termed wideband beam gain, which is given by the minimum beamforming gain over the entire frequency band given a target angle. Based on this metric, a wideband analog beamforming codebook design problem is formulated for optimally balancing the beamforming gains in both the spatial and frequency domains, and the performance loss of conventional narrowband beamforming in wideband systems is analyzed. To solve the new wideband beamforming codebook design problem, we divide the spatial domain into orthogonal angular zones each associated with one beam, thereby decoupling the codebook design into a zone division sub-problem and a set of beamforming optimization sub-problems each for one zone. For the zone division sub-problem, we propose a bisection method to obtain the optimal boundaries for separating adjacent zones. While for each of the per-zone-based beamforming optimization sub-problems, we further propose an efficient augmented Lagrange method (ALM) to solve it. Numerical results demonstrate the performance superiority of our proposed codebook design for wideband analog beamforming to the narrowband beamforming codebook and also validate our performance analysis.

Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios

In recent years, AI-based software engineering has progressed from pre-trained models to advanced agentic workflows, with Software Development Agents representing the next major leap. These agents, capable of reasoning, planning, and interacting with external environments, offer promising solutions to complex software engineering tasks. However, while much research has evaluated code generated by large language models (LLMs), comprehensive studies on agent-generated patches, particularly in real-world settings, are lacking. This study addresses that gap by evaluating 4,892 patches from 10 top-ranked agents on 500 real-world GitHub issues from SWE-Bench Verified, focusing on their impact on code quality. Our analysis shows no single agent dominated, with 170 issues unresolved, indicating room for improvement. Even for patches that passed unit tests and resolved issues, agents made different file and function modifications compared to the gold patches from repository developers, revealing limitations in the benchmark's test case coverage. Most agents maintained code reliability and security, avoiding new bugs or vulnerabilities; while some agents increased code complexity, many reduced code duplication and minimized code smells. Finally, agents performed better on simpler codebases, suggesting that breaking complex tasks into smaller sub-tasks could improve effectiveness. This study provides the first comprehensive evaluation of agent-generated patches on real-world GitHub issues, offering insights to advance AI-driven software development.

TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text

Current Retrieval-Augmented Generation (RAG) systems concatenate and process numerous retrieved document chunks for prefill which requires a large volume of computation, therefore leading to significant latency in time-to-first-token (TTFT). To reduce the computation overhead as well as TTFT, we introduce TurboRAG, a novel RAG system that redesigns the inference paradigm of the current RAG system by first pre-computing and storing the key-value (KV) caches of documents offline, and then directly retrieving the saved KV cache for prefill. Hence, online computation of KV caches is eliminated during inference. In addition, we provide a number of insights into the mask matrix and positional embedding mechanisms, plus fine-tune a pretrained language model to maintain model accuracy of TurboRAG. Our approach is applicable to most existing large language models and their applications without any requirement in modification of models and inference systems. Experimental results across a suite of RAG benchmarks demonstrate that TurboRAG reduces TTFT by up to 9.4x compared to the conventional RAG systems (on an average of 8.6x), but reserving comparable performance to the standard RAG systems.