In this paper, we propose an efficient transformer architecture that uses reinforced positional embedding to obtain superior performance with half the number of encoder decoder layers. We demonstrate that concatenating positional encoding with trainable token embeddings, normalizing columns in the token embedding matrix, and using the normalized token embedding matrix as the value of the attention layer improve the training and validation loss and the training time in an encoder-decoder Transformer model for a Portuguese-English translation task with 10 epochs or 12 hours of training across 10 trials. Our method, with roughly a threefold parameter reduction compared to the baseline model, yields a mean training loss of 1.21, a mean validation loss of 1.51, and an average training time of 1352.27 seconds per epoch, surpassing the baseline model with the same embedding dimension that employs addition of positional encoding and token embeddings, which achieves a mean training loss of 1.96, a validation loss of 2.18, and an average training time of 4297.79 seconds per epoch. Additionally, we evaluated our proposed architecture and the baseline across 14 diverse translation datasets from TensorFlow. The results indicate that our method consistently achieves lower or comparable training and validation losses, suggesting enhanced learning efficiency.
Large language models (LLMs) have driven significant advancements across diverse NLP tasks, with long-context models gaining prominence for handling extended inputs. However, the expanding key-value (KV) cache size required by Transformer architectures intensifies the memory constraints, particularly during the decoding phase, creating a significant bottleneck. Existing sparse attention mechanisms designed to address this bottleneck have two limitations: (1) they often fail to reliably identify the most relevant tokens for attention, and (2) they overlook the spatial coherence of token selection across consecutive Transformer layers, which can lead to performance degradation and substantial overhead in token selection. This paper introduces TidalDecode, a simple yet effective algorithm and system for fast and accurate LLM decoding through position persistent sparse attention. TidalDecode leverages the spatial coherence of tokens selected by existing sparse attention methods and introduces a few token selection layers that perform full attention to identify the tokens with the highest attention scores, while all other layers perform sparse attention with the pre-selected tokens. This design enables TidalDecode to substantially reduce the overhead of token selection for sparse attention without sacrificing the quality of the generated results. Evaluation on a diverse set of LLMs and tasks shows that TidalDecode closely matches the generative performance of full attention methods while reducing the LLM decoding latency by up to 2.1x.
Unlearning methods have the potential to improve the privacy and safety of large language models (LLMs) by removing sensitive or harmful information post hoc. The LLM unlearning research community has increasingly turned toward empirical benchmarks to assess the effectiveness of such methods. In this paper, we find that existing benchmarks provide an overly optimistic and potentially misleading view on the effectiveness of candidate unlearning methods. By introducing simple, benign modifications to a number of popular benchmarks, we expose instances where supposedly unlearned information remains accessible, or where the unlearning process has degraded the model's performance on retained information to a much greater extent than indicated by the original benchmark. We identify that existing benchmarks are particularly vulnerable to modifications that introduce even loose dependencies between the forget and retain information. Further, we show that ambiguity in unlearning targets in existing benchmarks can easily lead to the design of methods that overfit to the given test queries. Based on our findings, we urge the community to be cautious when interpreting benchmark results as reliable measures of progress, and we provide several recommendations to guide future LLM unlearning research.
Physical layer message authentication in underwater acoustic networks (UWANs) leverages the characteristics of the underwater acoustic channel (UWAC) as a fingerprint of the transmitting device. However, as the device moves its UWAC changes, and the authentication mechanism must track such variations. In this paper, we propose a context-based authentication mechanism operating in two steps: first, we estimate the position of the underwater device, then we predict its future position based on the previously estimated ones. To check the authenticity of the transmission, we compare the estimated and the predicted position. The location is estimated using a convolutional neural network taking as input the sample covariance matrix of the estimated UWACs. The prediction uses either a Kalman filter or a recurrent neural network (RNN). The authentication check is performed on the squared error between the predicted and estimated positions. The solution based on the Kalman filter outperforms that built on the RNN when the device moves according to a correlated Gauss-Markov mobility model, which reproduces a typical underwater motion.
In this paper, performance of a lossy cooperative unmanned aerial vehicle (UAV) relay communication system is analyzed. In this system, the UAV relay adopts lossy forward (LF) strategy and the receiver has certain distortion requirements for the received information. For the system described above, we first derive the achievable rate distortion region of the system. Then, on the basis of the region analysis, the system outage probability when the channel suffers Nakagami-$m$ fading is analyzed. Finally, we design an optimal relay position identification algorithm based on the Soft Actor-Critic (SAC) algorithm, which determines the optimal UAV position to minimize the outage probability. The simulation results show that the proposed algorithm can optimize the UAV position and reduce the system outage probability effectively.
Map-free LiDAR localization systems accurately localize within known environments by predicting sensor position and orientation directly from raw point clouds, eliminating the need for large maps and descriptors. However, their long training times hinder rapid adaptation to new environments. To address this, we propose FlashMix, which uses a frozen, scene-agnostic backbone to extract local point descriptors, aggregated with an MLP mixer to predict sensor pose. A buffer of local descriptors is used to accelerate training by orders of magnitude, combined with metric learning or contrastive loss regularization of aggregated descriptors to improve performance and convergence. We evaluate FlashMix on various LiDAR localization benchmarks, examining different regularizations and aggregators, demonstrating its effectiveness for rapid and accurate LiDAR localization in real-world scenarios. The code is available at https://github.com/raktimgg/FlashMix.
In future wireless networks, the availability of information on the position of mobile agents and the propagation environment can enable new services and increase the throughput and robustness of communications. Multipath-based simultaneous localization and mapping (SLAM) aims at estimating the position of agents and reflecting features in the environment by exploiting the relationship between the local geometry and multipath components (MPCs) in received radio signals. Existing multipath-based SLAM methods preprocess received radio signals using a channel estimator. The channel estimator lowers the data rate by extracting a set of dispersion parameters for each MPC. These parameters are then used as measurements for SLAM. Bayesian estimation for multipath-based SLAM is facilitated by the lower data rate. However, due to finite resolution capabilities limited by signal bandwidth, channel estimation is prone to errors and MPC parameters may be extracted incorrectly and lead to a reduced SLAM performance. We propose a multipath-based SLAM approach that directly uses received radio signals as inputs. A new statistical model that can effectively be represented by a factor graph is introduced. The factor graph is the starting point for the development of an efficient belief propagation (BP) method for multipath-based SLAM that avoids data preprocessing by a channel estimator. Numerical results based on synthetic and real data in challenging single-input, single-output (SISO) scenarios demonstrate that the proposed method outperforms conventional methods in terms of localization and mapping accuracy.
Six-dimensional movable antenna (6DMA) is an innovative technology to improve wireless network capacity by adjusting 3D positions and 3D rotations of antenna surfaces based on channel spatial distribution. However, the existing works on 6DMA have assumed a central processing unit (CPU) to jointly process the signals of all 6DMA surfaces to execute various tasks. This inevitably incurs prohibitively high processing cost for channel estimation. Therefore, we propose a distributed 6DMA processing architecture to reduce processing complexity of CPU by equipping each 6DMA surface with a local processing unit (LPU). In particular, we unveil for the first time a new \textbf{\textit{directional sparsity}} property of 6DMA channels, where each user has significant channel gains only for a (small) subset of 6DMA position-rotation pairs, which can receive direct/reflected signals from users. In addition, we propose a practical three-stage protocol for the 6DMA-equipped base station (BS) to conduct statistical CSI acquisition for all 6DMA candidate positions/rotations, 6DMA position/rotation optimization, and instantaneous channel estimation for user data transmission with optimized 6DMA positions/rotations. Specifically, the directional sparsity is leveraged to develop distributed algorithms for joint sparsity detection and channel power estimation, as well as for directional sparsity-aided instantaneous channel estimation. Using the estimated channel power, we develop a channel power-based optimization algorithm to maximize the ergodic sum rate of the users by optimizing the antenna positions/rotations. Simulation results show that our channel estimation algorithms are more accurate than benchmarks with lower pilot overhead, and our optimization outperforms fluid/movable antennas optimized only in two dimensions (2D), even when the latter have perfect instantaneous CSI.
This paper extends the optimal-trading framework developed in arXiv:2409.03586v1 to compute optimal strategies with real-world constraints. The aim of the current paper, as with the previous, is to study trading in the context of multi-player non-cooperative games. While the former paper relies on methods from the calculus of variations and optimal strategies arise as the solution of partial differential equations, the current paper demonstrates that the entire framework may be re-framed as a quadratic programming problem and cast in this light constraints are readily incorporated into the calculation of optimal strategies. An added benefit is that two-trader equilibria may be calculated as the end-points of a dynamic process of traders forming repeated adjustments to each other's strategy.
Since videos record objects moving coherently, adjacent video frames have commonness (similar object appearances) and uniqueness (slightly changed postures). To prevent redundant modeling of common video signals, we propose a novel diffusion-based framework, named COMUNI, which decomposes the COMmon and UNIque video signals to enable efficient video generation. Our approach separates the decomposition of video signals from the task of video generation, thus reducing the computation complexity of generative models. In particular, we introduce CU-VAE to decompose video signals and encode them into latent features. To train CU-VAE in a self-supervised manner, we employ a cascading merge module to reconstitute video signals and a time-agnostic video decoder to reconstruct video frames. Then we propose CU-LDM to model latent features for video generation, which adopts two specific diffusion streams to simultaneously model the common and unique latent features. We further utilize additional joint modules for cross modeling of the common and unique latent features, and a novel position embedding method to ensure the content consistency and motion coherence of generated videos. The position embedding method incorporates spatial and temporal absolute position information into the joint modules. Extensive experiments demonstrate the necessity of decomposing common and unique video signals for video generation and the effectiveness and efficiency of our proposed method.
The feed-forward based 3D Gaussian Splatting method has demonstrated exceptional capability in real-time human novel view synthesis. However, existing approaches are restricted to dense viewpoint settings, which limits their flexibility in free-viewpoint rendering across a wide range of camera view angle discrepancies. To address this limitation, we propose a real-time pipeline named EVA-Gaussian for 3D human novel view synthesis across diverse camera settings. Specifically, we first introduce an Efficient cross-View Attention (EVA) module to accurately estimate the position of each 3D Gaussian from the source images. Then, we integrate the source images with the estimated Gaussian position map to predict the attributes and feature embeddings of the 3D Gaussians. Moreover, we employ a recurrent feature refiner to correct artifacts caused by geometric errors in position estimation and enhance visual fidelity.To further improve synthesis quality, we incorporate a powerful anchor loss function for both 3D Gaussian attributes and human face landmarks. Experimental results on the THuman2.0 and THumansit datasets showcase the superiority of our EVA-Gaussian approach in rendering quality across diverse camera settings. Project page: https://zhenliuzju.github.io/huyingdong/EVA-Gaussian.
Large language models (LLMs) demonstrate exceptional capabilities in various scenarios. However, they suffer from much redundant information and are sensitive to the position of key information in long context scenarios. To address these challenges, we present Perception Compressor, a training-free prompt compression framework. It includes a perception retriever that leverages guiding questions and instruction to retrieve the most relevant demonstrations, a dual-slope ratio allocator to dynamically allocate compression ratios and open-book ratios, and a semi-guided iterative compression that retains key information at the token level while removing tokens that distract the LLM. We conduct extensive experiments on long context benchmarks, i.e., NaturalQuestions, LongBench, and MuSiQue. Experiment results show that Perception Compressor outperforms existing methods by a large margin, achieving state-of-the-art performance.
Oriented object detection in remote sensing images is a challenging task due to objects being distributed in multi-orientation. Recently, end-to-end transformer-based methods have achieved success by eliminating the need for post-processing operators compared to traditional CNN-based methods. However, directly extending transformers to oriented object detection presents three main issues: 1) objects rotate arbitrarily, necessitating the encoding of angles along with position and size; 2) the geometric relations of oriented objects are lacking in self-attention, due to the absence of interaction between content and positional queries; and 3) oriented objects cause misalignment, mainly between values and positional queries in cross-attention, making accurate classification and localization difficult. In this paper, we propose an end-to-end transformer-based oriented object detector, consisting of three dedicated modules to address these issues. First, Gaussian positional encoding is proposed to encode the angle, position, and size of oriented boxes using Gaussian distributions. Second, Wasserstein self-attention is proposed to introduce geometric relations and facilitate interaction between content and positional queries by utilizing Gaussian Wasserstein distance scores. Third, oriented cross-attention is proposed to align values and positional queries by rotating sampling points around the positional query according to their angles. Experiments on six datasets DIOR-R, a series of DOTA, HRSC2016 and ICDAR2015 show the effectiveness of our approach. Compared with previous end-to-end detectors, the OrientedFormer gains 1.16 and 1.21 AP$_{50}$ on DIOR-R and DOTA-v1.0 respectively, while reducing training epochs from 3$\times$ to 1$\times$. The codes are available at https://github.com/wokaikaixinxin/OrientedFormer.
Understanding and predicting pedestrian crossing behavioral intention is crucial for the driving safety of autonomous vehicles. Nonetheless, challenges emerge when using promising images or environmental context masks to extract various factors for time-series network modeling, causing pre-processing errors or a loss of efficiency. Typically, pedestrian positions captured by onboard cameras are often distorted and do not accurately reflect their actual movements. To address these issues, GTransPDM -- a Graph-embedded Transformer with a Position Decoupling Module -- was developed for pedestrian crossing intention prediction by leveraging multi-modal features. First, a positional decoupling module was proposed to decompose pedestrian lateral motion and encode depth cues in the image view. Then, a graph-embedded Transformer was designed to capture the spatio-temporal dynamics of human pose skeletons, integrating essential factors such as position, skeleton, and ego-vehicle motion. Experimental results indicate that the proposed method achieves 92% accuracy on the PIE dataset and 87% accuracy on the JAAD dataset, with a processing speed of 0.05ms. It outperforms the state-of-the-art in comparison.
Accurate camera calibration is a well-known and widely used task in computer vision that has been researched for decades. However, the standard approach based on checkerboard calibration patterns has some drawbacks that limit its applicability. For example, the calibration pattern must be completely visible without any occlusions. Alternative solutions such as ChArUco boards allow partial occlusions, but require a higher camera resolution due to the fine details of the position encoding. We present a new calibration pattern that combines the advantages of checkerboard calibration patterns with a lightweight position coding that can be decoded at very low resolutions. The decoding algorithm includes error correction and is computationally efficient. The whole approach is backward compatible to both checkerboard calibration patterns and several checkerboard calibration algorithms. Furthermore, the method can be used not only for camera calibration but also for camera pose estimation and marker-based object localization tasks.
Large language models (LLMs) enhanced with retrieval-augmented generation (RAG) have introduced a new paradigm for web search. However, the limited context awareness of LLMs degrades their performance on RAG tasks. Existing methods to enhance context awareness are often inefficient, incurring time or memory overhead during inference, and many are tailored to specific position embeddings. In this paper, we propose Position-Embedding-Agnostic attention Re-weighting (PEAR), which enhances the context awareness of LLMs with zero inference overhead. Specifically, on a proxy task focused on context copying, we first detect heads which suppress the models' context awareness thereby diminishing RAG performance. To weaken the impact of these heads, we re-weight their outputs with learnable coefficients. The LLM (with frozen parameters) is optimized by adjusting these coefficients to minimize loss on the proxy task. As a result, the coefficients are optimized to values less than one, thereby reducing their tendency to suppress RAG performance. During inference, the optimized coefficients are fixed to re-weight these heads, regardless of the specific task at hand. Our proposed PEAR offers two major advantages over previous approaches: (1) It introduces zero additional inference overhead in terms of memory usage or inference time, while outperforming competitive baselines in accuracy and efficiency across various RAG tasks. (2) It is independent of position embedding algorithms, ensuring broader applicability.
We introduce BRIDGET, a novel human-in-the-loop system for hybrid decision-making, aiding the user to label records from an un-labeled dataset, attempting to ``bridge the gap'' between the two most popular Hybrid Decision-Making paradigms: those featuring the human in a leading position, and the other with a machine making most of the decisions. BRIDGET understands when either a machine or a human user should be in charge, dynamically switching between two statuses. In the different statuses, BRIDGET still fosters the human-AI interaction, either having a machine learning model assuming skeptical stances towards the user and offering them suggestions, or towards itself and calling the user back. We believe our proposal lays the groundwork for future synergistic systems involving a human and a machine decision-makers.
Multi-view egocentric hand tracking is a challenging task and plays a critical role in VR interaction. In this report, we present a method that uses multi-view input images and camera extrinsic parameters to estimate both hand shape and pose. To reduce overfitting to the camera layout, we apply crop jittering and extrinsic parameter noise augmentation. Additionally, we propose an offline neural smoothing post-processing method to further improve the accuracy of hand position and pose. Our method achieves 13.92mm MPJPE on the Umetrack dataset and 21.66mm MPJPE on the HOT3D dataset.
While NLP research into hate speech detection has grown exponentially in the last three decades, there has been minimal uptake or engagement from policy makers and non-profit organisations. We argue the absence of ethical frameworks have contributed to this rift between current practice and best practice. By adopting appropriate ethical frameworks, NLP researchers may enable the social impact potential of hate speech research. This position paper is informed by reviewing forty-eight hate speech detection systems associated with thirty-seven publications from different venues.
Capturing different intensity and directions of light rays at the same scene Light field (LF) can encode the 3D scene cues into a 4D LF image which has a wide range of applications (i.e. post-capture refocusing and depth sensing). LF image super-resolution (SR) aims to improve the image resolution limited by the performance of LF camera sensor. Although existing methods have achieved promising results the practical application of these models is limited because they are not lightweight enough. In this paper we propose a lightweight model named LGFN which integrates the local and global features of different views and the features of different channels for LF image SR. Specifically owing to neighboring regions of the same pixel position in different sub-aperture images exhibit similar structural relationships we design a lightweight CNN-based feature extraction module (namely DGCE) to extract local features better through feature modulation. Meanwhile as the position beyond the boundaries in the LF image presents a large disparity we propose an efficient spatial attention module (namely ESAM) which uses decomposable large-kernel convolution to obtain an enlarged receptive field and an efficient channel attention module (namely ECAM). Compared with the existing LF image SR models with large parameter our model has a parameter of 0.45M and a FLOPs of 19.33G which has achieved a competitive effect. Extensive experiments with ablation studies demonstrate the effectiveness of our proposed method which ranked the second place in the Track 2 Fidelity & Efficiency of NTIRE2024 Light Field Super Resolution Challenge and the seventh place in the Track 1 Fidelity.