Yichuan Ma, Linyang Li, Yongkang Chen, Peiji Li, Xiaozhe Li, Qipeng Guo, Dahua Lin, Kai Chen. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

With the emergence of Multimodal Large Language Models (MLLMs), hundreds of benchmarks have been developed to ensure the reliability of MLLMs in downstream tasks. However, the evaluation mechanism itself may not be reliable. For developers of MLLMs, questions remain about which benchmark to use and whether the test results meet their requirements. Therefore, we propose a critical principle of Information Density, which examines how much insight a benchmark can provide for the development of MLLMs. We characterize it from four key dimensions: (1) Fallacy, (2) Difficulty, (3) Redundancy, (4) Diversity. Through a comprehensive analysis of more than 10,000 samples, we measured the information density of 19 MLLM benchmarks. Experiments show that using the latest benchmarks in testing can provide more insight compared to previous ones, but there is still room for improvement in their information density. We hope this principle can promote the development and application of future MLLM benchmarks. Project page: https://github.com/lcysyzxdxc/bench4bench

Simultaneous wireless information and power transfer (SWIPT) is regarded as the enabling technology for IoT, 5G and beyond, or even 6G. Resonant beam system (RBS) is a promising candidate to provide high-power, long-range, and intrinsically safe SWIPT. Yet ensuring human safety under high-power application scenarios is still challenging. In this paper, we propose a portable auto-protection (AP) scheme to enhance the safety of RBS. Leveraging self-mixing interference, the high-power resonant beam is automatically cut off as the low-power protective beam is obstructed by foreign objects, resulting in less radiation exposure to invading objects. The paper proposes a phase compensation scheme that resolves the contradiction between portability and interference-induced mode variation, allowing the receiver to be placed anywhere within the field of view. Moreover, by approximating the cavity to Fabry-Pérot interferometer, analytical models are established to reveal the safety-enhancement mechanism and evaluate the system performance. Numerical results demonstrate that the AP scheme will not significantly compromise the portability and SWIPT performance of RBS, as the average spectral efficiency and electric power are 13.55bps/Hz and 5.42W respectively, within 6m transmission distance.

Multi-scale detection based on Feature Pyramid Networks (FPN) has been a popular approach in object detection to improve accuracy. However, using multi-layer features in the decoder of FPN methods entails performing many convolution operations on high-resolution feature maps, which consumes significant computational resources. In this paper, we propose a novel perspective for FPN in which we directly use fused single-layer features for regression and classification. Our proposed model, You Only Look One Hourglass (YOLOH), fuses multiple feature maps into one feature map in the encoder. We then use dense connections and dilated residual blocks to expand the receptive field of the fused feature map. This output not only contains information from all the feature maps, but also has a multi-scale receptive field for detection. The experimental results on the COCO dataset demonstrate that YOLOH achieves higher accuracy and better run-time performance than established detector baselines, for instance, it achieves an average precision (AP) of 50.2 on a standard 3× training schedule and achieves 40.3 AP at a speed of 32 FPS on the ResNet-50 model. We anticipate that YOLOH can serve as a reference for researchers to design real-time detection in future studies. Our code is available at https://github.com/wsb853529465/YOLOH-main.

Age of Information (AoI) is a recently introduced metric to capture data freshness. In this article, we consider a multiuser single-destination Internet of Things (IoT) system with periodic state updating, and investigate the scheduling methods of minimizing the long-term average AoI with limited retransmission times. In view of the retransmission mode, the AoI optimization problems for retransmission with and without feedback are analyzed. For the retransmission without feedback, we formulate the expected decision loss (EDL) function of the AoI optimization problem with the finite retransmission times and propose a loss-greedy policy by minimizing the EDL at each step. For the retransmission with feedback, a potential optimal solution is to construct the AoI optimization problem as an infinite-horizon Markov decision process (MDP) and solve the corresponding Bellman optimal equations. However, this optimal solution is prone to suffer from the curse of dimensionality and is hard to implement. To address this issue, we decouple the infinite-horizon MDP into the finite-state MDP in each single frame, and then propose a low-complexity slot-based max-weight (SBMW) policy to minimize the long-term average AoI. Numerical results show that, compared with an ALOHA-like baseline policy, the proposed Loss-Greedy policy can achieve up to 48% reduction of the average AoI for the retransmission without feedback, while the SBMW policy can reduce the average AoI by 57% in the retransmission with feedback. The average performance gain of the proposed policies over the state-of-the-art policies is at least 10%.