arXiv subjects

Yi Yang

Publications and source records attributed to Yi Yang.

At least 595 records · Page 33Linked to original sources

arXiv2024

Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models

One fascinating aspect of pre-trained vision-language models~(VLMs) learning under language supervision is their impressive zero-shot generalization capability. However, this ability is hindered by distribution shifts between the training and testing data. Previous test time adaptation~(TTA) methods for VLMs in zero-shot classification rely on minimizing the entropy of model outputs, tending to be stuck in incorrect model predictions. In this work, we propose TTA with feedback to rectify the model output and prevent the model from becoming blindly confident. Specifically, a CLIP model is adopted as the reward model during TTA and provides feedback for the VLM. Given a single test sample, the VLM is forced to maximize the CLIP reward between the input and sampled results from the VLM output distribution. The proposed \textit{reinforcement learning with CLIP feedback~(RLCF)} framework is highly flexible and universal. Beyond the classification task, with task-specific sampling strategies and a proper reward baseline choice, RLCF can be easily extended to not only discrimination tasks like retrieval but also generalization tasks like image captioning, improving the zero-shot generalization capacity of VLMs. According to the characteristics of these VL tasks, we build different fully TTA pipelines with RLCF to improve the zero-shot generalization ability of various VLMs. Extensive experiments along with promising empirical results demonstrate the effectiveness of RLCF. The code is available at https://github.com/mzhaoshuai/RLCF.

cs.CV↗

arXiv2024

Disentangling Structured Components: Towards Adaptive, Interpretable and Scalable Time Series Forecasting

Multivariate time-series (MTS) forecasting is a paramount and fundamental problem in many real-world applications. The core issue in MTS forecasting is how to effectively model complex spatial-temporal patterns. In this paper, we develop a adaptive, interpretable and scalable forecasting framework, which seeks to individually model each component of the spatial-temporal patterns. We name this framework SCNN, as an acronym of Structured Component-based Neural Network. SCNN works with a pre-defined generative process of MTS, which arithmetically characterizes the latent structure of the spatial-temporal patterns. In line with its reverse process, SCNN decouples MTS data into structured and heterogeneous components and then respectively extrapolates the evolution of these components, the dynamics of which are more traceable and predictable than the original MTS. Extensive experiments are conducted to demonstrate that SCNN can achieve superior performance over state-of-the-art models on three real-world datasets. Additionally, we examine SCNN with different configurations and perform in-depth analyses of the properties of SCNN.

cs.LG↗

arXiv2024

Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States

Large Language Models (LLMs) can make up answers that are not real, and this is known as hallucination. This research aims to see if, how, and to what extent LLMs are aware of hallucination. More specifically, we check whether and how an LLM reacts differently in its hidden states when it answers a question right versus when it hallucinates. To do this, we introduce an experimental framework which allows examining LLM's hidden states in different hallucination situations. Building upon this framework, we conduct a series of experiments with language models in the LLaMA family (Touvron et al., 2023). Our empirical findings suggest that LLMs react differently when processing a genuine response versus a fabricated one. We then apply various model interpretation techniques to help understand and explain the findings better. Moreover, informed by the empirical observations, we show great potential of using the guidance derived from LLM's hidden representation space to mitigate hallucination. We believe this work provides insights into how LLMs produce hallucinated answers and how to make them occur less often.

cs.CL↗

arXiv2024

A seven-Earth-radius helium-burning star inside a 20.5-min detached binary

Binary evolution theory predicts that the second common envelope (CE) ejection can produce low-mass (0.32-0.36 Msun) subdwarf B (sdB) stars inside ultrashort-orbital-period binary systems, as their helium cores are ignited under nondegenerate conditions. With the orbital decay driven by gravitational-wave (GW) radiation, the minimum orbital periods of detached sdB binaries could be as short as ~20 minutes. However, only four sdB binaries with orbital periods below an hour have been reported so far, while none of them has an orbital period approaching the above theoretical limit. Here we report the discovery of a 20.5-minute-orbital-period ellipsoidal binary, TMTS J052610.43+593445.1, in which the visible star is being tidally deformed by an invisible carbon-oxygen white dwarf (WD) companion. The visible component is inferred to be an sdB star with a mass of ~0.33 Msun, approaching that of helium-ignition limit, although a He-core WD cannot be completely ruled out. In particular, the radius of this low-mass sdB star is only 0.066 Rsun, about seven Earth radii, possibly representing the most compact nondegenerate star ever known. Such a system provides a key clue to map the binary evolution scheme from the second CE ejection to the formation of AM CVn stars having a helium-star donor, and it will also serve as a crucial verification binary of space-borne GW detectors in the future.

astro-ph.SR↗

arXiv2024

Modeling the black holes surrounded by a dark matter halo in the galactic center of M87

In this paper, the structure of a dark matter halo can be well described by the mass model of M87 and the Einasto profile for the cold dark matter model, i.e., $ρ_{\text{eina}} (r)=ρ_\text{e} \exp ( -2 α^{-1} ((r/r_\text{e})^α-1 ) )$ (Wang et al. in Nature 585:39-42, 2020). Under these conditions, we construct a solution of a static spherically symmetric black hole in a dark matter halo. Then, using the Newman-janis algorithm, we extend this static solution to the case of rotation, and obtain a solution for the Kerr-like black hole. We prove that this solution of the Kerr-like black hole is indeed a solution to the Einstein field equations. Finally, taking M87 as an example, we study and analyze some physical properties of this Kerr-like black hole, and then compare them with the Kerr black hole. Particularly, from the perspective of the black hole shadow and the fact that the Kerr-like black hole and the Kerr black hole is distinguishable, we give the upper limit of the shape parameter of the Einasto density profile, that is approximately $α<0.22$, which may provide a new method to further improve and perfect the density profile of dark matter model. These research results for the black hole in a dark matter halo may indirectly provide an effective method for detecting the existence of dark matter.

gr-qc↗

arXiv2024

Retrosynthesis prediction enhanced by in-silico reaction data augmentation

Recent advances in machine learning (ML) have expedited retrosynthesis research by assisting chemists to design experiments more efficiently. However, all ML-based methods consume substantial amounts of paired training data (i.e., chemical reaction: product-reactant(s) pair), which is costly to obtain. Moreover, companies view reaction data as a valuable asset and restrict the accessibility to researchers. These issues prevent the creation of more powerful retrosynthesis models due to their data-driven nature. As a response, we exploit easy-to-access unpaired data (i.e., one component of product-reactant(s) pair) for generating in-silico paired data to facilitate model training. Specifically, we present RetroWISE, a self-boosting framework that employs a base model inferred from real paired data to perform in-silico reaction generation and augmentation using unpaired data, ultimately leading to a superior model. On three benchmark datasets, RetroWISE achieves the best overall performance against state-of-the-art models (e.g., +8.6% top-1 accuracy on the USPTO-50K test dataset). Moreover, it consistently improves the prediction accuracy of rare transformations. These results show that Retro- WISE overcomes the training bottleneck by in-silico reactions, thereby paving the way toward more effective ML-based retrosynthesis models.

cs.LG↗

arXiv2024

DeFlow: Decoder of Scene Flow Network in Autonomous Driving

Scene flow estimation determines a scene's 3D motion field, by predicting the motion of points in the scene, especially for aiding tasks in autonomous driving. Many networks with large-scale point clouds as input use voxelization to create a pseudo-image for real-time running. However, the voxelization process often results in the loss of point-specific features. This gives rise to a challenge in recovering those features for scene flow tasks. Our paper introduces DeFlow which enables a transition from voxel-based features to point features using Gated Recurrent Unit (GRU) refinement. To further enhance scene flow estimation performance, we formulate a novel loss function that accounts for the data imbalance between static and dynamic points. Evaluations on the Argoverse 2 scene flow task reveal that DeFlow achieves state-of-the-art results on large-scale point cloud data, demonstrating that our network has better performance and efficiency compared to others. The code is open-sourced at https://github.com/KTH-RPL/deflow.

cs.CV↗

arXiv2024

MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries

Retrieval-augmented generation (RAG) augments large language models (LLM) by retrieving relevant knowledge, showing promising potential in mitigating LLM hallucinations and enhancing response quality, thereby facilitating the great adoption of LLMs in practice. However, we find that existing RAG systems are inadequate in answering multi-hop queries, which require retrieving and reasoning over multiple pieces of supporting evidence. Furthermore, to our knowledge, no existing RAG benchmarking dataset focuses on multi-hop queries. In this paper, we develop a novel dataset, MultiHop-RAG, which consists of a knowledge base, a large collection of multi-hop queries, their ground-truth answers, and the associated supporting evidence. We detail the procedure of building the dataset, utilizing an English news article dataset as the underlying RAG knowledge base. We demonstrate the benchmarking utility of MultiHop-RAG in two experiments. The first experiment compares different embedding models for retrieving evidence for multi-hop queries. In the second experiment, we examine the capabilities of various state-of-the-art LLMs, including GPT-4, PaLM, and Llama2-70B, in reasoning and answering multi-hop queries given the evidence. Both experiments reveal that existing RAG methods perform unsatisfactorily in retrieving and answering multi-hop queries. We hope MultiHop-RAG will be a valuable resource for the community in developing effective RAG systems, thereby facilitating greater adoption of LLMs in practice. The MultiHop-RAG and implemented RAG system is publicly available at https://github.com/yixuantt/MultiHop-RAG/.

cs.CL↗

arXiv2024

Black hole surrounded by the pseudo-isothermal dark matter halo

The abundance of dark matter in the actual universe motivates us to construct the black hole spacetime enveloped by dark matter. In this paper, we derive a new spherically symmetric black hole surrounded by the pseudo-isothermal dark matter halo, and then explore the effects of the pseudo-isothermal halo profile on a rotating black hole at the M87 galactic center, aiming to achieve a black hole solution that aligns with those found in the real universe. Using the Newman-Janis method, we derive a rotating black hole solution encompassed by the pseudo-isothermal halo, which is consistent with observations of actual black holes that are believed to possess spin. Our investigation focuses on the impact of the pseudo-isothermal halo on the black hole event horizon, time-like and null orbits, as well as the black hole shadow. We find that as the spin parameter $a$ increases, the interval between the inner event horizon and the outer event horizon of the rotating black hole surrounded by the pseudo-isothermal halo in M87 diminishes. This leads to the formation of an extreme black hole. The presence of dark matter, however, has minimal effect on the event horizon. Moreover, in the M87 as the spin parameter $a$ increases, the black hole shadow deviates increasingly from a standard circle, with larger spin parameters causing more pronounced distortion relative to the standard circle. Surprisingly, we observe that the dark matter density has very little influence on the shadow of the black hole surrounded by the pseudo-isothermal halo in the M87. This study contributes to a deeper understanding of black hole structures and the role of dark matter in the universe.

gr-qc↗

arXiv2024

Product-Level Try-on: Characteristics-preserving Try-on with Realistic Clothes Shading and Wrinkles

Image-based virtual try-on systems,which fit new garments onto human portraits,are gaining research attention.An ideal pipeline should preserve the static features of clothes(like textures and logos)while also generating dynamic elements(e.g.shadows,folds)that adapt to the model's pose and environment.Previous works fail specifically in generating dynamic features,as they preserve the warped in-shop clothes trivially with predicted an alpha mask by composition.To break the dilemma of over-preserving and textures losses,we propose a novel diffusion-based Product-level virtual try-on pipeline,\ie PLTON, which can preserve the fine details of logos and embroideries while producing realistic clothes shading and wrinkles.The main insights are in three folds:1)Adaptive Dynamic Rendering:We take a pre-trained diffusion model as a generative prior and tame it with image features,training a dynamic extractor from scratch to generate dynamic tokens that preserve high-fidelity semantic information. Due to the strong generative power of the diffusion prior,we can generate realistic clothes shadows and wrinkles.2)Static Characteristics Transformation: High-frequency Map(HF-Map)is our fundamental insight for static representation.PLTON first warps in-shop clothes to the target model pose by a traditional warping network,and uses a high-pass filter to extract an HF-Map for preserving static cloth features.The HF-Map is used to generate modulation maps through our static extractor,which are injected into a fixed U-net to synthesize the final result.To enhance retention,a Two-stage Blended Denoising method is proposed to guide the diffusion process for correct spatial layout and color.PLTON is finetuned only with our collected small-size try-on dataset.Extensive quantitative and qualitative experiments on 1024 768 datasets demonstrate the superiority of our framework in mimicking real clothes dynamics.

cs.CV↗

arXiv2024

ClawCraneNet: Leveraging Object-level Relation for Text-based Video Segmentation

Text-based video segmentation is a challenging task that segments out the natural language referred objects in videos. It essentially requires semantic comprehension and fine-grained video understanding. Existing methods introduce language representation into segmentation models in a bottom-up manner, which merely conducts vision-language interaction within local receptive fields of ConvNets. We argue that such interaction is not fulfilled since the model can barely construct region-level relationships given partial observations, which is contrary to the description logic of natural language/referring expressions. In fact, people usually describe a target object using relations with other objects, which may not be easily understood without seeing the whole video. To address the issue, we introduce a novel top-down approach by imitating how we human segment an object with the language guidance. We first figure out all candidate objects in videos and then choose the refereed one by parsing relations among those high-level objects. Three kinds of object-level relations are investigated for precise relationship understanding, i.e., positional relation, text-guided semantic relation, and temporal relation. Extensive experiments on A2D Sentences and J-HMDB Sentences show our method outperforms state-of-the-art methods by a large margin. Qualitative results also show our results are more explainable.

cs.CV↗

arXiv2024

Rethinking Cross-modal Interaction from a Top-down Perspective for Referring Video Object Segmentation

Referring video object segmentation (RVOS) aims to segment video objects with the guidance of natural language reference. Previous methods typically tackle RVOS through directly grounding linguistic reference over the image lattice. Such bottom-up strategy fails to explore object-level cues, easily leading to inferior results. In this work, we instead put forward a two-stage, top-down RVOS solution. First, an exhaustive set of object tracklets is constructed by propagating object masks detected from several sampled frames to the entire video. Second, a Transformer-based tracklet-language grounding module is proposed, which models instance-level visual relations and cross-modal interactions simultaneously and efficiently. Our model ranks first place on CVPR2021 Referring Youtube-VOS challenge.

cs.CV↗

arXiv2024

DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval

Text-video retrieval is a critical multi-modal task to find the most relevant video for a text query. Although pretrained models like CLIP have demonstrated impressive potential in this area, the rising cost of fully finetuning these models due to increasing model size continues to pose a problem. To address this challenge, prompt tuning has emerged as an alternative. However, existing works still face two problems when adapting pretrained image-text models to downstream video-text tasks: (1) The visual encoder could only encode frame-level features and failed to extract global-level general video information. (2) Equipping the visual and text encoder with separated prompts failed to mitigate the visual-text modality gap. To this end, we propose DGL, a cross-modal Dynamic prompt tuning method with Global-Local video attention. In contrast to previous prompt tuning methods, we employ the shared latent space to generate local-level text and frame prompts that encourage inter-modal interaction. Furthermore, we propose modeling video in a global-local attention mechanism to capture global video information from the perspective of prompt tuning. Extensive experiments reveal that when only 0.67% parameters are tuned, our cross-modal prompt tuning strategy DGL outperforms or is comparable to fully finetuning methods on MSR-VTT, VATEX, LSMDC, and ActivityNet datasets. Code will be available at https://github.com/knightyxp/DGL

cs.CV↗

arXiv2024

Local-Global Context Aware Transformer for Language-Guided Video Segmentation

We explore the task of language-guided video segmentation (LVS). Previous algorithms mostly adopt 3D CNNs to learn video representation, struggling to capture long-term context and easily suffering from visual-linguistic misalignment. In light of this, we present Locater (local-global context aware Transformer), which augments the Transformer architecture with a finite memory so as to query the entire video with the language expression in an efficient manner. The memory is designed to involve two components -- one for persistently preserving global video content, and one for dynamically gathering local temporal context and segmentation history. Based on the memorized local-global context and the particular content of each frame, Locater holistically and flexibly comprehends the expression as an adaptive query vector for each frame. The vector is used to query the corresponding frame for mask generation. The memory also allows Locater to process videos with linear time complexity and constant size memory, while Transformer-style self-attention computation scales quadratically with sequence length. To thoroughly examine the visual grounding capability of LVS models, we contribute a new LVS dataset, A2D-S+, which is built upon A2D-S dataset but poses increased challenges in disambiguating among similar objects. Experiments on three LVS datasets and our A2D-S+ show that Locater outperforms previous state-of-the-arts. Further, we won the 1st place in the Referring Video Object Segmentation Track of the 3rd Large-scale Video Object Segmentation Challenge, where Locater served as the foundation for the winning solution. Our code and dataset are available at: https://github.com/leonnnop/Locater

cs.CV↗

arXiv2024

Newly Formed Dust within the Circumstellar Environment of SNIa-CSM 2018evt

Dust associated with various stellar sources in galaxies at all cosmic epochs remains a controversial topic, particularly whether supernovae (SNe) play an important role in dust production. We report evidence of dust formation in the cold, dense shell behind the ejecta-circumstellar medium (CSM) interaction in the Type Ia-CSM SN 2018evt three years after the explosion, characterized by a rise in the mid-infrared (MIR) emission accompanied by an accelerated decline in the optical radiation of the SN. Such a dust-formation picture is also corroborated by the concurrent evolution of the profiles of the Ha emission line. Our model suggests enhanced CSM dust concentration at increasing distances from the SN as compared to what can be expected from the density profile of the mass loss from a steady stellar wind. By the time of the last MIR observations at day +1041, a total amount of 1.2+-0.2x10^{-2} Msun of new dust has been formed by SN 2018evt, making SN 2018evt one of the most prolific dust factories among SNe with evidence of dust formation. The unprecedented witness of the intense production procedure of dust may shed light on the perceptions of dust formation in cosmic history.

astro-ph.HE↗

arXiv2024

MS-DETR: Efficient DETR Training with Mixed Supervision

DETR accomplishes end-to-end object detection through iteratively generating multiple object candidates based on image features and promoting one candidate for each ground-truth object. The traditional training procedure using one-to-one supervision in the original DETR lacks direct supervision for the object detection candidates. We aim at improving the DETR training efficiency by explicitly supervising the candidate generation procedure through mixing one-to-one supervision and one-to-many supervision. Our approach, namely MS-DETR, is simple, and places one-to-many supervision to the object queries of the primary decoder that is used for inference. In comparison to existing DETR variants with one-to-many supervision, such as Group DETR and Hybrid DETR, our approach does not need additional decoder branches or object queries. The object queries of the primary decoder in our approach directly benefit from one-to-many supervision and thus are superior in object candidate prediction. Experimental results show that our approach outperforms related DETR variants, such as DN-DETR, Hybrid DETR, and Group DETR, and the combination with related DETR variants further improves the performance.

cs.CV↗

arXiv2024

Rotating black hole mimicker surrounded by the string cloud

Traversable wormholes and regular black holes usually represent completely different scenarios. But in the black bounce spacetime they can be described by a same line element, which is very attractive. Furthermore, the black hole photos taken by EHT show that black holes have spin, so spin is an indispensable intrinsic property of black holes in the actual universe. In this work, we derive a rotating black hole mimicker surrounded by the string cloud (SC), which can be interpolated to represent regular black hole spacetime and traversable wormhole spacetime. We investigate the effect of the spin $a$ and SC parameter $L$ on the observables (shadow radius $R_s$ and distortion $δ_s$) and energy emission rate of the black hole mimicker surrounded by the SC. We find that shadow for this spacetime is very sensitive to the $L$, i.e., the SC parameter can significantly increase the boundary of the shadow.

gr-qc↗

arXiv2023

SEEAvatar: Photorealistic Text-to-3D Avatar Generation with Constrained Geometry and Appearance

Powered by large-scale text-to-image generation models, text-to-3D avatar generation has made promising progress. However, most methods fail to produce photorealistic results, limited by imprecise geometry and low-quality appearance. Towards more practical avatar generation, we present SEEAvatar, a method for generating photorealistic 3D avatars from text with SElf-Evolving constraints for decoupled geometry and appearance. For geometry, we propose to constrain the optimized avatar in a decent global shape with a template avatar. The template avatar is initialized with human prior and can be updated by the optimized avatar periodically as an evolving template, which enables more flexible shape generation. Besides, the geometry is also constrained by the static human prior in local parts like face and hands to maintain the delicate structures. For appearance generation, we use diffusion model enhanced by prompt engineering to guide a physically based rendering pipeline to generate realistic textures. The lightness constraint is applied on the albedo texture to suppress incorrect lighting effect. Experiments show that our method outperforms previous methods on both global and local geometry and appearance quality by a large margin. Since our method can produce high-quality meshes and textures, such assets can be directly applied in classic graphics pipeline for realistic rendering under any lighting condition. Project page at: https://yoxu515.github.io/SEEAvatar/.

cs.CV↗