Search

We investigate the host galaxy properties of eight little red dots (LRDs) selected from the JWST UNCOVER survey, applying a new technique ({\tt\string GalfitS}) to simultaneously fit the morphology and spectral energy distribution using multi-band NIRCam images covering $\sim 1-4\,\mu {\rm m}$. We detect the host galaxy in only one LRD, MSAID38108 at $z = 4.96$, which has a stellar mass of $\log (M_*/M_{\odot}) = 8.66^{+0.24}_{-0.23}$, an effective radius $R_e=0.66^{+0.08}_{-0.05}$ kpc, and a S\'ersic index $n=0.71^{+0.07}_{-0.08}$. No host emission centered on the central point source is found in the other seven LRDs. We derive stringent upper limits for the stellar mass of a hypothetical host galaxy by conducting realistic mock simulations that place high-redshift galaxy images under the LRDs. Based on the black hole masses estimated from the broad H$\alpha$ emission line, the derived stellar mass limits are at least a factor of 10 lower than expected from the $z \approx 0$ scaling relation between black hole mass and host galaxy stellar mass. Intriguingly, four of the LRDs (50\% of the sample) show extended, off-centered emission, which is particularly prominent in the bluer bands. The asymmetric emission of two sources can be modeled as stellar emission, but the nature of the other two is unclear., Comment: 29 pages, 15 figures, submitted to ApJ

Miniaturized spectrometers for Raman spectroscopy have the potential to open up a new chapter in sensing. Raman spectroscopy is essential for material characterization and biomedical diagnostics, however, its weak signal and the need for sub-nanometer resolution pose challenges. Conventional spectrometers, with footprints proportional to optical throughput and resolution, are difficult to integrate into compact devices such as wearables. Waveguide-based Fourier Transform Spectrometers (FTS) enable compact spectrometers, and multi-aperture designs can achieve high throughput for applications such as Raman spectroscopy, however, experimental research in this domain remains limited. In this work, we present a multi-aperture SiN waveguide-based FTS overcoming these limitations and enabling Raman spectroscopy of isopropyl alcohol, glucose, Paracetamol, and Ibuprofen with enhanced throughput. Our spectrometer chip, fabricated on a 200 mm SiN wafer, with 160 edge-coupled waveguide apertures connected to an array of ultra-compact interferometers and a small footprint of just 1.6 mm x 4.8 mm, achieves a spectral range of 40 nm and a resolution of 0.5 nm. Experimental results demonstrate that least absolute shrinkage and selection operator (LASSO) regression significantly enhances Raman spectrum reconstruction. Our work on waveguide-based spectrometry paves the way for integrating accurate and compact Raman sensors into consumer electronics and space exploration instruments., Comment: 13 pages, 5 figures, Corresponding Authors: Sarp Kerman (sarp.kerman@photonicview.com), Chang Chen (changchen@sjtu.edu.cn)

The spontaneous conversion of muonium to antimuonium is one of the interesting charged lepton flavor violation phenomena, offering a sensitive probe of potential new physics and serving as a tool to constrain the parameter space beyond the Standard Model. Utilizing a high-intensity muon beam, a Michel electron magnetic spectrometer and a positron transport solenoid together with a positron detection system, MACE aims to discover or constrain this rare process at the conversion probability beyond the level of $10^{-13}$. This report provides an overview of the theoretical framework and detailed experimental design in the search for the muonium-to-antimuonium conversion., Comment: 115 pages, 59 figures

Current exploration methods struggle to search for shops in unknown open-world environments due to a lack of prior knowledge and text recognition capabilities. Venue maps offer valuable information that can aid exploration planning by correlating scene signage with map data. However, the arbitrary shapes and styles of the text on signage, along with multi-view inconsistencies, pose significant challenges for accurate recognition by robots. Additionally, the discrepancies between real-world environments and venue maps hinder the incorporation of text information into planners. This paper introduces a novel signage-aware exploration system to address these challenges, enabling the robot to utilize venue maps effectively. We propose a signage understanding method that accurately detects and recognizes the text on signage using a diffusion-based text instance retrieval method combined with a 2D-to-3D semantic fusion strategy. Furthermore, we design a venue map-guided exploration-exploitation planner that balances exploration in unknown regions using a directional heuristic derived from venue maps with exploitation to get close and adjust orientation for better recognition. Experiments in large-scale shopping malls demonstrate our method's superior signage recognition accuracy and coverage efficiency, outperforming state-of-the-art scene text spotting methods and traditional exploration methods., Comment: 8 pages, 9 figures, 4 tables, under review

Recent advances in Video Large Language Models (Video-LLMs) have demonstrated their great potential in general-purpose video understanding. To verify the significance of these models, a number of benchmarks have been proposed to diagnose their capabilities in different scenarios. However, existing benchmarks merely evaluate models through video-level question-answering, lacking fine-grained event-level assessment and task diversity. To fill this gap, we introduce E.T. Bench (Event-Level & Time-Sensitive Video Understanding Benchmark), a large-scale and high-quality benchmark for open-ended event-level video understanding. Categorized within a 3-level task taxonomy, E.T. Bench encompasses 7.3K samples under 12 tasks with 7K videos (251.4h total length) under 8 domains, providing comprehensive evaluations. We extensively evaluated 8 Image-LLMs and 12 Video-LLMs on our benchmark, and the results reveal that state-of-the-art models for coarse-level (video-level) understanding struggle to solve our fine-grained tasks, e.g., grounding event-of-interests within videos, largely due to the short video context length, improper time representations, and lack of multi-event training data. Focusing on these issues, we further propose a strong baseline model, E.T. Chat, together with an instruction-tuning dataset E.T. Instruct 164K tailored for fine-grained event-level understanding. Our simple but effective solution demonstrates superior performance in multiple scenarios., Comment: Accepted to NeurIPS 2024 Datasets and Benchmarks Track

Traditional in the wild image quality assessment (IQA) models are generally trained with the quality labels of mean opinion score (MOS), while missing the rich subjective quality information contained in the quality ratings, for example, the standard deviation of opinion scores (SOS) or even distribution of opinion scores (DOS). In this paper, we propose a novel IQA method named RichIQA to explore the rich subjective rating information beyond MOS to predict image quality in the wild. RichIQA is characterized by two key novel designs: (1) a three-stage image quality prediction network which exploits the powerful feature representation capability of the Convolutional vision Transformer (CvT) and mimics the short-term and long-term memory mechanisms of human brain; (2) a multi-label training strategy in which rich subjective quality information like MOS, SOS and DOS are concurrently used to train the quality prediction network. Powered by these two novel designs, RichIQA is able to predict the image quality in terms of a distribution, from which the mean image quality can be subsequently obtained. Extensive experimental results verify that the three-stage network is tailored to predict rich quality information, while the multi-label training strategy can fully exploit the potentials within subjective quality rating and enhance the prediction performance and generalizability of the network. RichIQA outperforms state-of-the-art competitors on multiple large-scale in the wild IQA databases with rich subjective rating labels. The code of RichIQA will be made publicly available on GitHub.

In this paper, we investigate the feasibility of leveraging large language models (LLMs) for integrating general knowledge and incorporating pseudo-events as priors for temporal content distribution in video moment retrieval (VMR) models. The motivation behind this study arises from the limitations of using LLMs as decoders for generating discrete textual descriptions, which hinders their direct application to continuous outputs like salience scores and inter-frame embeddings that capture inter-frame relations. To overcome these limitations, we propose utilizing LLM encoders instead of decoders. Through a feasibility study, we demonstrate that LLM encoders effectively refine inter-concept relations in multimodal embeddings, even without being trained on textual embeddings. We also show that the refinement capability of LLM encoders can be transferred to other embeddings, such as BLIP and T5, as long as these embeddings exhibit similar inter-concept similarity patterns to CLIP embeddings. We present a general framework for integrating LLM encoders into existing VMR architectures, specifically within the fusion module. Through experimental validation, we demonstrate the effectiveness of our proposed methods by achieving state-of-the-art performance in VMR. The source code can be accessed at https://github.com/fletcherjiang/LLMEPET., Comment: Accepted to ACM Multimedia 2024

Image resampling is a basic technique that is widely employed in daily applications, such as camera photo editing. Recent deep neural networks (DNNs) have made impressive progress in performance by introducing learned data priors. Still, these methods are not the perfect substitute for interpolation, due to the drawbacks in efficiency and versatility. In this work, we propose a novel method of Learning Resampling Function (termed LeRF), which takes advantage of both the structural priors learned by DNNs and the locally continuous assumption of interpolation. Specifically, LeRF assigns spatially varying resampling functions to input image pixels and learns to predict the hyper-parameters that determine the shapes of these resampling functions with a neural network. Based on the formulation of LeRF, we develop a family of models, including both efficiency-orientated and performance-orientated ones. To achieve interpolation-level efficiency, we adopt look-up tables (LUTs) to accelerate the inference of the learned neural network. Furthermore, we design a directional ensemble strategy and edge-sensitive indexing patterns to better capture local structures. On the other hand, to obtain DNN-level performance, we propose an extension of LeRF to enable it in cooperation with pre-trained upsampling models for cascaded resampling. Extensive experiments show that the efficiency-orientated version of LeRF runs as fast as interpolation, generalizes well to arbitrary transformations, and outperforms interpolation significantly, e.g., up to 3dB PSNR gain over Bicubic for x2 upsampling on Manga109. Besides, the performance-orientated version of LeRF reaches comparable performance with existing DNNs at much higher efficiency, e.g., less than 25% running time on a desktop GPU., Comment: Code: https://github.com/ddlee-cn/LeRF-PyTorch

This paper proposes a practical method to monitor power system inertia using Pumped Storage Hydropower (PSH) switching-off events. This approach offers real-time system-level inertia estimation with minimal expenses, no disruption, and the inclusion of behind-the-meter inertia. First, accurate inertia estimation is achieved through improved RoCoF calculation that accounts for pre-event RoCoF, reducing common random frequency fluctuations in practice. Second, PSH field data is analyzed, highlighting the benefits of using switching-off events for grid inertia estimation. Third, an event detection trigger is designed to capture pump switching-off events based on local and system features. Fourth, the method is validated on the U.S. Eastern Interconnection model with over 60,000 buses, demonstrating very high accuracy (3%-5% error rate). Finally, it is applied to the U.S. Western Interconnection, with field validation showing a 9.9% average absolute error rate. Despite challenges in practical power system inertia estimation, this method enhances decision-making for power grid reliability and efficiency, addressing challenges posed by renewable energy integration., Comment: 8 pages, 15 figures

Large language models (LLMs) now support extremely long context windows, but the quadratic complexity of vanilla attention results in significantly long Time-to-First-Token (TTFT) latency. Existing approaches to address this complexity require additional pretraining or finetuning, and often sacrifice model accuracy. In this paper, we first provide both theoretical and empirical foundations for near-lossless sparse attention. We find dynamically capturing head-specific sparse patterns at runtime with low overhead is crucial. To address this, we propose SampleAttention, an adaptive structured and near-lossless sparse attention. Leveraging observed significant sparse patterns, SampleAttention attends to a fixed percentage of adjacent tokens to capture local window patterns, and employs a two-stage query-guided key-value filtering approach, which adaptively select a minimum set of key-values with low overhead, to capture column stripe patterns. Comprehensive evaluations show that SampleAttention can seamlessly replace vanilla attention in off-the-shelf LLMs with nearly no accuracy loss, and reduces TTFT by up to $2.42\times$ compared with FlashAttention.

Despite the recent advancements in offline RL, no unified algorithm could achieve superior performance across a broad range of tasks. Offline \textit{value function learning}, in particular, struggles with sparse-reward, long-horizon tasks due to the difficulty of solving credit assignment and extrapolation errors that accumulates as the horizon of the task grows.~On the other hand, models that can perform well in long-horizon tasks are designed specifically for goal-conditioned tasks, which commonly perform worse than value function learning methods on short-horizon, dense-reward scenarios. To bridge this gap, we propose a hierarchical planner designed for offline RL called PlanDQ. PlanDQ incorporates a diffusion-based planner at the high level, named D-Conductor, which guides the low-level policy through sub-goals. At the low level, we used a Q-learning based approach called the Q-Performer to accomplish these sub-goals. Our experimental results suggest that PlanDQ can achieve superior or competitive performance on D4RL continuous control benchmark tasks as well as AntMaze, Kitchen, and Calvin as long-horizon tasks.

We study the algebra of observables in semiclassical quantum gravity for cosmological backgrounds, focusing on two key examples: slow-roll inflation and evaporating Schwarzschild-de Sitter black holes. In both cases, we demonstrate the existence of a nontrivial algebra of diffeomorphism-invariant observables \emph{without} the introduction of an external clock system or the presence of any asymptotic gravitational charges. Instead, the rolling inflaton field and the evaporating black hole act as physical clocks that allow a definition of gauge-invariant observables at $G = 0$. The resulting algebras are both Type II$_\infty$ factors, but neither is manifestly a crossed product algebra. We establish a connection between the Type II entropy of these algebras and generalized entropies for appropriate states. Our work extends previous results on Type II gravitational algebras and highlights the crucial role of out-of-equilibrium dynamics for defining gauge-invariant observables in semiclassical canonically quantised gravity. We also briefly discuss the construction of gauge-invariant algebras for compact wedges bounded by extremal surfaces in generic spacetimes (i.e. in the absence of any Killing symmetry). In contrast to the inflaton and black hole cases, this algebra does end up being a simple crossed product. No clock or asymptotic charges are required because of the absence of any symmetry in the classical background., Comment: 58 pages + appendices, 9 figures; v2: fix typos

Layout generation is the keystone in achieving automated graphic design, requiring arranging the position and size of various multi-modal design elements in a visually pleasing and constraint-following manner. Previous approaches are either inefficient for large-scale applications or lack flexibility for varying design requirements. Our research introduces a unified framework for automated graphic layout generation, leveraging the multi-modal large language model (MLLM) to accommodate diverse design tasks. In contrast, our data-driven method employs structured text (JSON format) and visual instruction tuning to generate layouts under specific visual and textual constraints, including user-defined natural language specifications. We conducted extensive experiments and achieved state-of-the-art (SOTA) performance on public multi-modal layout generation benchmarks, demonstrating the effectiveness of our method. Moreover, recognizing existing datasets' limitations in capturing the complexity of real-world graphic designs, we propose two new datasets for much more challenging tasks (user-constrained generation and complicated poster), further validating our model's utility in real-life settings. Marking by its superior accessibility and adaptability, this approach further automates large-scale graphic design tasks. The code and datasets will be publicly available on https://github.com/posterllava/PosterLLaVA., Comment: 10 pages; typos corrected, appendix added

Efficient visual perception using mobile systems is crucial, particularly in unknown environments such as search and rescue operations, where swift and comprehensive perception of objects of interest is essential. In such real-world applications, objects of interest are often situated in complex environments, making the selection of the 'Next Best' view based solely on maximizing visibility gain suboptimal. Semantics, providing a higher-level interpretation of perception, should significantly contribute to the selection of the next viewpoint for various perception tasks. In this study, we formulate a novel information gain that integrates both visibility gain and semantic gain in a unified form to select the semantic-aware Next-Best-View. Additionally, we design an adaptive strategy with termination criterion to support a two-stage search-and-acquisition manoeuvre on multiple objects of interest aided by a multi-degree-of-freedoms (Multi-DoFs) mobile system. Several semantically relevant reconstruction metrics, including perspective directivity and region of interest (ROI)-to-full reconstruction volume ratio, are introduced to evaluate the performance of the proposed approach. Simulation experiments demonstrate the advantages of the proposed approach over existing methods, achieving improvements of up to 27.13% for the ROI-to-full reconstruction volume ratio and a 0.88234 average perspective directivity. Furthermore, the planned motion trajectory exhibits better perceiving coverage toward the target.

We study the critical behaviors of the ground and first excited states in the one-dimensional nonreciprocal Aubry-Andr{\'e}-Harper model using both the self-normal and biorthogonal fidelity susceptibilities. We demonstrate that fidelity susceptibilities serve as a probe for the phase transition in the nonreciprocal AAH model. For ground states, characterized by real eigenenergies across the entire regime, both fidelity susceptibilities near the critical points scale as $N^{2}$, akin to the Hermitian AAH model. However, for the first-excited states, where $\mathcal{PT}$ transitions occur, the fidelity susceptibilities exhibit distinct scaling laws, contingent upon whether the lattice consists of even or odd sites. For even lattices, both the self-normal and and biorthogonal fidelity susceptibilities near the critical points continue to scale as $N^{2}$. In contrast, for odd lattices, the biorthogonal fidelity susceptibilities diverge, while the self-normal fidelity susceptibilities exhibit linear behavior, indicating a novel scaling law., Comment: 7 pages, 4 figures

Although visual navigation has been extensively studied using deep reinforcement learning, online learning for real-world robots remains a challenging task. Recent work directly learned from offline dataset to achieve broader generalization in the real-world tasks, which, however, faces the out-of-distribution (OOD) issue and potential robot localization failures in a given map for unseen observation. This significantly drops the success rates and even induces collision. In this paper, we present a self-correcting visual navigation method, SCALE, that can autonomously prevent the robot from the OOD situations without human intervention. Specifically, we develop an image-goal conditioned offline reinforcement learning method based on implicit Q-learning (IQL). When facing OOD observation, our novel localization recovery method generates the potential future trajectories by learning from the navigation affordance, and estimates the future novelty via random network distillation (RND). A tailored cost function searches for the candidates with the least novelty that can lead the robot to the familiar places. We collect offline data and conduct evaluation experiments in three real-world urban scenarios. Experiment results show that SCALE outperforms the previous state-of-the-art methods for open-world navigation with a unique capability of localization recovery, significantly reducing the need for human intervention. Code is available at https://github.com/KubeEdge4Robotics/ScaleNav., Comment: 7 pages, 5 figures, 2024 IEEE International Conference on Robotics and Automation

Video temporal grounding (VTG) is a fine-grained video understanding problem that aims to ground relevant clips in untrimmed videos given natural language queries. Most existing VTG models are built upon frame-wise final-layer CLIP features, aided by additional temporal backbones (e.g., SlowFast) with sophisticated temporal reasoning mechanisms. In this work, we claim that CLIP itself already shows great potential for fine-grained spatial-temporal modeling, as each layer offers distinct yet useful information under different granularity levels. Motivated by this, we propose Reversed Recurrent Tuning ($R^2$-Tuning), a parameter- and memory-efficient transfer learning framework for video temporal grounding. Our method learns a lightweight $R^2$ Block containing only 1.5% of the total parameters to perform progressive spatial-temporal modeling. Starting from the last layer of CLIP, $R^2$ Block recurrently aggregates spatial features from earlier layers, then refines temporal correlation conditioning on the given query, resulting in a coarse-to-fine scheme. $R^2$-Tuning achieves state-of-the-art performance across three VTG tasks (i.e., moment retrieval, highlight detection, and video summarization) on six public benchmarks (i.e., QVHighlights, Charades-STA, Ego4D-NLQ, TACoS, YouTube Highlights, and TVSum) even without the additional backbone, demonstrating the significance and effectiveness of the proposed scheme. Our code is available at https://github.com/yeliudev/R2-Tuning., Comment: ECCV 2024 Camera Ready

Autonomous driving progress relies on large-scale annotated datasets. In this work, we explore the potential of generative models to produce vast quantities of freely-labeled data for autonomous driving applications and present SubjectDrive, the first model proven to scale generative data production in a way that could continuously improve autonomous driving applications. We investigate the impact of scaling up the quantity of generative data on the performance of downstream perception models and find that enhancing data diversity plays a crucial role in effectively scaling generative data production. Therefore, we have developed a novel model equipped with a subject control mechanism, which allows the generative model to leverage diverse external data sources for producing varied and useful data. Extensive evaluations confirm SubjectDrive's efficacy in generating scalable autonomous driving training data, marking a significant step toward revolutionizing data production methods in this field., Comment: Project page: https://subjectdrive.github.io/

Diffusion Transformer (DiT) has emerged as the new trend of generative diffusion models on image generation. In view of extremely slow convergence in typical DiT, recent breakthroughs have been driven by mask strategy that significantly improves the training efficiency of DiT with additional intra-image contextual learning. Despite this progress, mask strategy still suffers from two inherent limitations: (a) training-inference discrepancy and (b) fuzzy relations between mask reconstruction & generative diffusion process, resulting in sub-optimal training of DiT. In this work, we address these limitations by novelly unleashing the self-supervised discrimination knowledge to boost DiT training. Technically, we frame our DiT in a teacher-student manner. The teacher-student discriminative pairs are built on the diffusion noises along the same Probability Flow Ordinary Differential Equation (PF-ODE). Instead of applying mask reconstruction loss over both DiT encoder and decoder, we decouple DiT encoder and decoder to separately tackle discriminative and generative objectives. In particular, by encoding discriminative pairs with student and teacher DiT encoders, a new discriminative loss is designed to encourage the inter-image alignment in the self-supervised embedding space. After that, student samples are fed into student DiT decoder to perform the typical generative diffusion task. Extensive experiments are conducted on ImageNet dataset, and our method achieves a competitive balance between training cost and generative capacity., Comment: CVPR 2024

Scaling multi-dimensional transformers to long sequences is indispensable across various domains. However, the challenges of large memory requirements and slow speeds of such sequences necessitate sequence parallelism. All existing approaches fall under the category of embedded sequence parallelism, which are limited to shard along a single sequence dimension, thereby introducing significant communication overhead. However, the nature of multi-dimensional transformers involves independent calculations across multiple sequence dimensions. To this end, we propose Dynamic Sequence Parallelism (DSP) as a novel abstraction of sequence parallelism. DSP dynamically switches the parallel dimension among all sequences according to the computation stage with efficient resharding strategy. DSP offers significant reductions in communication costs, adaptability across modules, and ease of implementation with minimal constraints. Experimental evaluations demonstrate DSP's superiority over state-of-the-art embedded sequence parallelism methods by remarkable throughput improvements ranging from 32.2% to 10x, with less than 25% communication volume.

While we enjoy the richness and informativeness of multimodal data, it also introduces interference and redundancy of information. To achieve optimal domain interpretation with limited resources, we propose CSDNet, a lightweight \textbf{C}ross \textbf{S}hallow and \textbf{D}eep Perception \textbf{Net}work designed to integrate two modalities with less coherence, thereby discarding redundant information or even modality. We implement our CSDNet for Salient Object Detection (SOD) task in robotic perception. The proposed method capitalises on spatial information prescreening and implicit coherence navigation across shallow and deep layers of the depth-thermal (D-T) modality, prioritising integration over fusion to maximise the scene interpretation. To further refine the descriptive capabilities of the encoder for the less-known D-T modalities, we also propose SAMAEP to guide an effective feature mapping to the generalised feature space. Our approach is tested on the VDT-2048 dataset, leveraging the D-T modality outperforms those of SOTA methods using RGB-T or RGB-D modalities for the first time, achieves comparable performance with the RGB-D-T triple-modality benchmark method with 5.97 times faster at runtime and demanding 0.0036 times fewer FLOPs. Demonstrates the proposed CSDNet effectively integrates the information from the D-T modality. The code will be released upon acceptance.

We consider a version of the typical state firewall setup recently reintroduced by Stanford and Yang, who found that wormholes may create firewalls. We examine a late-time double scaling limit in JT gravity in which one can resum the expansion in the number of wormholes, and we use this to study the exact distribution of interior slices at times exponential in the entropy. We consider a thermofield double with and without early perturbations on a boundary. These perturbations can appear on interior slices as dangerous high energy shocks. For exponentially late times, wormholes tend to teleport the particles created by perturbations and render the interior more dangerous. In states with many perturbations separated by large times, the probability of a safe interior is exponentially small. Such states thus almost certainly have firewalls at the horizon, even though they would be safe without wormholes. With perturbation, even in the safest state we conceive, the odds of encountering a firewall are fifty-fifty. One interpretation of the phenomena found here is that wormholes can change time-ordered contours into effective out-of-time-ordered folds, making shockwaves appear in unexpected places., Comment: 48 pages; minor clarifications, matches published version

Diffusion-based generative methods have proven effective in modeling trajectories with offline datasets. However, they often face computational challenges and can falter in generalization, especially in capturing temporal abstractions for long-horizon tasks. To overcome this, we introduce the Hierarchical Diffuser, a simple, fast, yet surprisingly effective planning method combining the advantages of hierarchical and diffusion-based planning. Our model adopts a "jumpy" planning strategy at the higher level, which allows it to have a larger receptive field but at a lower computational cost -- a crucial factor for diffusion-based planning methods, as we have empirically verified. Additionally, the jumpy sub-goals guide our low-level planner, facilitating a fine-tuning stage and further improving our approach's effectiveness. We conducted empirical evaluations on standard offline reinforcement learning benchmarks, demonstrating our method's superior performance and efficiency in terms of training and planning speed compared to the non-hierarchical Diffuser as well as other hierarchical planning methods. Moreover, we explore our model's generalization capability, particularly on how our method improves generalization capabilities on compositional out-of-distribution tasks.

Computational spectral imaging is drawing increasing attention owing to the snapshot advantage, and amplitude, phase, and wavelength encoding systems are three types of representative implementations. Fairly comparing and understanding the performance of these systems is essential, but challenging due to the heterogeneity in encoding design. To overcome this limitation, we propose the unified encoding model (UEM) that covers all physical systems using the three encoding types. Specifically, the UEM comprises physical amplitude, physical phase, and physical wavelength encoding models that can be combined with a digital decoding model in a joint encoder-decoder optimization framework to compare the three systems under a unified experimental setup fairly. Furthermore, we extend the UEMs to ideal versions, namely, ideal amplitude, ideal phase, and ideal wavelength encoding models, which are free from physical constraints, to explore the full potential of the three types of computational spectral imaging systems. Finally, we conduct a holistic comparison of the three types of computational spectral imaging systems and provide valuable insights for designing and exploiting these systems in the future.

Spectral super-resolution that aims to recover hyperspectral image (HSI) from easily obtainable RGB image has drawn increasing interest in the field of computational photography. The crucial aspect of spectral super-resolution lies in exploiting the correlation within HSIs. However, two types of bottlenecks in existing Transformers limit performance improvement and practical applications. First, existing Transformers often separately emphasize either spatial-wise or spectral-wise correlation, disrupting the 3D features of HSI and hindering the exploitation of unified spatial-spectral correlation. Second, existing self-attention mechanism always establishes full-rank correlation matrix by learning the correlation between pairs of tokens, leading to its inability to describe linear dependence widely existing in HSI among multiple tokens. To address these issues, we propose a novel Exhaustive Correlation Transformer (ECT) for spectral super-resolution. First, we propose a Spectral-wise Discontinuous 3D (SD3D) splitting strategy, which models unified spatial-spectral correlation by integrating spatial-wise continuous splitting strategy and spectral-wise discontinuous splitting strategy. Second, we propose a Dynamic Low-Rank Mapping (DLRM) model, which captures linear dependence among multiple tokens through a dynamically calculated low-rank dependence map. By integrating unified spatial-spectral attention and linear dependence, our ECT can model exhaustive correlation within HSI. The experimental results on both simulated and real data indicate that our method achieves state-of-the-art performance. Codes and pretrained models will be available later.

The attractive interaction between $J/\psi$ and $\psi(3770)$ has to be strong enough to form the molecular resonant structure, i.e., $X(6900)$. We argue that since $\psi(3770)$ decays predominantly into a $D\bar D$ pair, the interactions between $J/\psi$ and $\psi(3770)$ may be significantly enhanced due to the three point $D\bar D$ loop diagram. The enhancement comes from the anomalous threshold located at $t=-1.288$GeV$^2$, which effect propagates into the $s$-channel partial wave amplitude in the vicinity of $\sqrt{s}\simeq 6.9$GeV. This effect may be helpful in forming the $X(6900)$ peak., Comment: 6 pages, 5 figures