text string | source string |
|---|---|
reverse goal order, which failed to progress through the curriculum. Importance of Ascending Difficulty. Structuring curriculums with ascending difficulty is essential, as front-loading too many challenges can overwhelm agents. For instance: •A curriculum with multiple versions of a goal arranged by ascending difficult... | https://arxiv.org/abs/2505.22531v1 |
arXiv:2505.22533v1 [cs.LG] 28 May 2025TabularQGAN: A Quantum Generative Model for Tabular Data Pallavi Bhardwaj∗1,3, Caitlin Jones∗2,3, Lasse Dierich1,4,5, Aleksandar Vučković3,6 1SAP SE, Walldorf, Germany 2BASF Digital Solutions, Ludwigshafen, Germany 3QUTAC, Quantum Technology and Application Consortium, Germany 4Tec... | https://arxiv.org/abs/2505.22533v1 |
task of a quantum computer is to produce a probability distribution that is sampled from, which is also what is required for a generative task [23]. Generative models are useful in cases whereby amplifying a sample population with generated samples can lead to improved statistics of rare events [ 24] (to be used in ano... | https://arxiv.org/abs/2505.22533v1 |
ability to learn the ground truth probability distribution and propose a quantum–classical generative adversarial network (QGAN), which has a similar structure to that of a conventional GAN, with the generator implemented using a variational quantum circuit (VQC) [38] and the discriminator is realized using a classical... | https://arxiv.org/abs/2505.22533v1 |
[U,N] = 0 whereNis the excitation number operator) can be decomposed into product of two-level unitary operators known as Givens rotations, Gij(θ,φ), such that U=/productdisplay mGimjm(θm,φm) (4) where Gij(θ,φ) = cosθ−eiφsinθ e−iφsinθ cosθ (5) is a gate acting on the subspace of qubit iandj, and index mruns over a... | https://arxiv.org/abs/2505.22533v1 |
non-Boolean circuit might be denoted as [n5,c3,c2], where n5 represents a numerical register with five qubits, c3 is a three-qubit one-hot register, and c2 is a two-qubit one-hot categorical register. In Boolean circuit design, the same configuration could be simplified to [n6,c3], where the binary category is absorbed... | https://arxiv.org/abs/2505.22533v1 |
. . initial excitation model layern5 c3 c2 (a) Non-Boolean design 0 1 2 3 4 5 6 7 8 9XRY RY RY RY RY RY G IsingYY G IsingYY IsingYYRY IsingYYRY IsingYYRY RY RY G. . .. . .. . .. . .. . .. . .. . .. . .. . . initial excitation model layern5 c3 (b) Boolean design Figure 1: Non-Boolean circuit design (a) and Boolean circu... | https://arxiv.org/abs/2505.22533v1 |
generated distributions, to log 19:it for each epoch for analysis: DKL(Preal∥Pgen) =/summationdisplay xPreal(x) logPreal(x) Pgen(x) 20:end for 2.6 Evaluation and Benchmarking Benchmarks: WebenchmarkourquantumgeneratoragainsttwoclassicalbaselinesCTGANandCopulaGAN. CTGAN is introduced in [ 33] and CopulaGAN via SDV libra... | https://arxiv.org/abs/2505.22533v1 |
Hyperparameter Optimization Hyperparameter optimization was performed over all four data sets for both the quantum and classical models. The optimization was performed via a grid search over the hyperparameters circuit depth, batch size, generator learning rate, discriminator learning rate, and, for the classical model... | https://arxiv.org/abs/2505.22533v1 |
Census 10TabularQGAN 0.949 0.869 0.026 80 CTGAN 0.855 0.953 0.112 131,072 CopulaGAN 0.845 0.953 0.105 65,536 Adults Census 15TabularQGAN 0.930 0.820 0.038 104 CTGAN 0.848 0.925 0.117 131,072 CopulaGAN 0.836 0.913 0.096 60 MIMIC 10TabularQGAN 0.983 0.973 0.006 88 CTGAN 0.888 0.984 0.068 65,536 CopulaGAN 0.887 0.981 0.06... | https://arxiv.org/abs/2505.22533v1 |
Training well-performing models for large-scale real-world applications can require expensive and energy-intensive computation. In this regime, the parameter compression provided by quantum models may dramatically reduce computational resources. For TabularQGAN to be a practically advantageous model, further investigat... | https://arxiv.org/abs/2505.22533v1 |
quantum interferometry. arXiv preprint arXiv:2408.08292 , 2024. [5]Peter W. Shor. Polynomial-time algorithms for prime factorization and discrete logarithms on a quantum computer. SIAM Journal on Computing , 26(5):1484–1509, 1997. [6]Lov K. Grover. A fast quantum mechanical algorithm for database search. In Proceedings... | https://arxiv.org/abs/2505.22533v1 |
Evandro F Fang, Wendy Cornell, Ruth Nussinov, and Feixiong Cheng. Deep generative molecular design reshapes drug discovery. Cell Reports Medicine , 3(12), 2022. [26]Ismail Keshta and Ammar Odeh. Security and privacy of electronic health records: Concerns and challenges. Egyptian Informatics Journal , 22(2):177–183, 202... | https://arxiv.org/abs/2505.22533v1 |
Bengio. Generative adversarial nets. In Z. Ghahramani, M. Welling, C. Cortes, N. Lawrence, and K.Q. Weinberger, editors, Advances in Neural Information Processing Systems , volume 27. Curran Associates, Inc., 2014. [45] Inc. DataCebo. Synthetic data metrics, 10 2023. Version 0.12.0, MIT License. [46]Tianqi Chen and Car... | https://arxiv.org/abs/2505.22533v1 |
set of all unique rows of the search space is given by S={0,..., 25−1}×{Income1,Income2}×{Workclass1,...,Workclass4}, (17) where×denotes the Cartesian product of two discrete sets. We assign an index to each of the |S|= 256 elements of the set and encode the index in binary using log2|S|= 8qubits. This allows us to rep... | https://arxiv.org/abs/2505.22533v1 |
the maximum overall metric for each dataset. For TabularQGAN we found that the deeper circuit depths were optimal and for the classical models, the lower number of layers was better. 15 Table 4: Best found hyperparameter configurations for each model and data type Data Set NameModel%Batch SizeCircuit DepthLR GenLR Disc... | https://arxiv.org/abs/2505.22533v1 |
(where the target feature was numeric). Again, these results are for a subsample of the overall hyperparameter-optimized data. We find 16 that, on average, the TabularQGAN models had a lower downstream score, indicating that those samples were better able to replicate the real data in training a classifier. This genera... | https://arxiv.org/abs/2505.22533v1 |
arXiv:2505.22543v1 [cs.CV] 28 May 2025Scaling-up Perceptual Video Quality Assessment Ziheng Jia1*, Zicheng Zhang1*, Zeyu Zhang1, Yingji Liang4, Xiaorong Zhu1, Chunyi Li1, Jinliang Han1 Haoning Wu3, Bin Wang2, Haoran Zhang2, Guanyu Zhu2, Qiyong Zhao2 Xiaohong Liu1, Xiongkuo Min1♢, Guangtao Zhai1 1Shanghai Jiaotong Unive... | https://arxiv.org/abs/2505.22543v1 |
our models achieve state-of-the-art per- formance in both quality understanding and rating tasks. 1. Introduction In the context of perceptual video quality assessment (VQA), the field currently focuses on two key tasks: quan- titative quality rating and quality understanding. Quality rating refers to assigning a preci... | https://arxiv.org/abs/2505.22543v1 |
OmniVQA-MOS-20K, a large-scale human-labeled UGC video subjective scoring dataset. • The proposed OmniVQA models achieve state-of-the-art (SOTA) performance by training LMMs with the task- specific complementary training strategy for both quality rating and understanding (general and fine-grained) tasks. • We introduce... | https://arxiv.org/abs/2505.22543v1 |
Voting Aesthetic Branch Construction Process High-quality Videos Spatial Temporal Distorted Videos with bboxsDistorted Object Semantic Description Distortion Information Recording (Center,upperleft...) (At ... second) (Last for... seconds) (Noticeable,...,Severe) Step2: Distorted Objects Recognition and Description Ste... | https://arxiv.org/abs/2505.22543v1 |
methods[33, 42, 44, 47] to label the objective quality labels for the candidate videos. To ensure consistency in the scale of the scores from each scoring method, they are first converted to[0,100) . Subsequently, the scores are averaged for each video as the objective quality label. 3.2. The technical branch The techn... | https://arxiv.org/abs/2505.22543v1 |
be: “The sharpness is poor with degraded human facial details.” Voting and post-processing. We use sota LMM to per- form voting to decide the post-processing method. We input the keyframe sequence sampled from the annotated video (1fps) along with the prior summary of each quality factor. We then prompt it to conduct 3... | https://arxiv.org/abs/2505.22543v1 |
Proportions of Annotation TypesSpatial- temporal~ 150 Temporal~ 350Spatial ~ 400 (c) Proportions of Quality Concerns in the Machine-annotated Part(d) Proportions of Quality Concerns in the Human-annotated PartSpatial- temporal ~ 46 Spatial ~ 145 Temporal~ 109 Figure 4. Statistical information of the OmniVQA-FG-Bench. m... | https://arxiv.org/abs/2505.22543v1 |
lower quality than the one in the bottom left. The building in the top right appears very blurry , while the building in the bottom left appears relatively clear . Quality Concern: Spatial Figure 5. Examples of questions and correct answers of the human-annotated part of the OmniVQA-FG-Benchmark . and6instruction Q&A p... | https://arxiv.org/abs/2505.22543v1 |
: Spatiotemporal quality encom- passes both spatial and temporal dimensions, focusing on quality issues that arise in specific locations or at semantic objects during specific timepoints or intervals. Detailed examples are shown in the supp. (Figs. 23 and 24). For the machine annotation , we select 900videos with objec... | https://arxiv.org/abs/2505.22543v1 |
that the datasets can provide valuable prior informa- tion for one another, thus making them well-suited to serve as mutually beneficial pre-training components. The pro- cess of complementary training is also depicted in Fig. 6. 7. Experiments We conduct a detailed evaluation of our models on video quality rating and ... | https://arxiv.org/abs/2505.22543v1 |
60.59% 51.27% 34.76% 47.31% Qwen2.5-vl (72B) 54.55% 49.48% 35.92% 46.03% 57.82% 47.96% 40.68% 46.39% 60.20% 48.17% 35.19% 47.62% 57.88% 54.73% 34.45% 48.21% GPT-4o (24-11-20) [1] 60.61% 50.17% 45.25% 50.89% 63.27% 52.04% 48.45% 51.89% 69.73% 48.48% 41.11% 51.27% 63.55% 59.09% 42.68% 53.25% Gemini-1.5-pro [34] 56.80% 43... | https://arxiv.org/abs/2505.22543v1 |
input the whole frame sequence of the video (resizing to(224∗224) to the motion extractor. The experimental results are presented in Tab. 2. The experimental results show that the chatter achieves the best Overall performance on both the testanddevsub- sets, with outstanding performance in the Tech., Aes., and Temp. qu... | https://arxiv.org/abs/2505.22543v1 |
human annotation tasks. This demonstrates the importance of the in-context branch in the MIDB for im- proving the model’s performance in fine-grained spatiotem- poral quality understanding tasks. 7.4. Discussions We have also conducted experiments on some key points, and further analysis is presented in the supp. (Sec.... | https://arxiv.org/abs/2505.22543v1 |
quality grounding with large multi-modality models. In ACM MM , pages 486–495, 2024. 2 [6] Tsai-Shien Chen, Aliaksandr Siarohin, Willi Menapace, Ekaterina Deyneka, Hsiang-wei Chao, Byung Eun Jeon, Yuwei Fang, Hsin-Ying Lee, Jian Ren, Ming-Hsuan Yang, et al. Panda-70m: Captioning 70m videos with multiple cross-modality ... | https://arxiv.org/abs/2505.22543v1 |
Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Zi- wei Liu, et al. Llava-onevision: Easy visual task transfer. arXiv preprint arXiv:2408.03326 , 2024. 7 [22] Dingquan Li, Tingting Jiang, and Ming Jiang. Quality as- sessment of in-the-wild videos. In ACM MM , pages 2351– 2359, 2019.... | https://arxiv.org/abs/2505.22543v1 |
[39] Yilin Wang, Junjie Ke, Hossein Talebi, Joong Gon Yim, Neil Birkbeck, Balu Adsumilli, Peyman Milanfar, and Feng Yang. Rich features for perceptual quality assessment of ugc videos. In CVPR , pages 13435–13444, 2021. 2 [40] Zhenhua Wang, Guang Xu, and Ming Ren. Llm- generated natural language meets scaling laws: New... | https://arxiv.org/abs/2505.22543v1 |
ECCV , pages 259–276. Springer, 2024. 2, 3 [54] Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, and Lucas Beyer. Sigmoid loss for language image pre-training. InICCV , pages 11975–11986, 2023. 6 [55] Biao Zhang, Zhongtao Liu, Colin Cherry, and Orhan Firat. When scaling meets llm finetuning: The effect of data, model... | https://arxiv.org/abs/2505.22543v1 |
the softmax function. The values ωrepresent the weight factors assigned to the normalized probabilities of each quality level, given by [1,0.75,0.5,0.25,0]. The resulting weighted sum of these probabilities produces the predicted quality score Q, which is confined within the range of [0,1]. We directly call model.forwa... | https://arxiv.org/abs/2505.22543v1 |
that the hyperparameter remains consistent across both rounds of complementary training. Model Structure/Training Hyper-Parameters Name/Value More Information Vision Tower SigLIP-SO400m Parameter size= 397.75M,Tokens per keyframe= 196 Vision Projector 2-layers MLP+GeLU Parameter size =16.98M Motion Extractor SlowFast-R... | https://arxiv.org/abs/2505.22543v1 |
understanding tasks. The former is easier to explain, as the amount of training data for the quality rating task is much smaller than that for the quality understanding task. Therefore, the pretraining effect for the quality understanding data is evi- dently stronger, leading to amore noticeable differences in the qual... | https://arxiv.org/abs/2505.22543v1 |
in Fig. 9. 1.Gaussian Blur (Blur) : The Gaussian blur effect smooths the image by applying a filter with a kernel size determined by the level. The larger the level, the stronger the blur effect. Blurred =GaussianBlur (Region ,(16×Level+1,16×Level+1),0) 2.Overexposure (Brightness Increase) : Overexposure in- creases th... | https://arxiv.org/abs/2505.22543v1 |
✗ / ✓ 115,214 Human-annotated MIDB for video quality understanding. OmniVQA-Chat-20K 20,000 ✓20,000 ✓ 20,000 Large-scale MIDB for quality rating for in-the-wild UGC videos OmniVQA-MOS-400K 86,716 ✗ / ✓ 402,987 Machine-dominated MIDB for video quality understanding. Incontext branch examples Fig. 19 illustrates 3annotat... | https://arxiv.org/abs/2505.22543v1 |
on different video qual- ity concerns: spatial, temporal, and spatiotemporal aspects. Human annotations include three types of questions: Yes- or-No, What/How, and Open-ended, while machine annota- tions consist of two types: Yes-or-No and What/How. G. Applications G.1. Potential future applications The most practical ... | https://arxiv.org/abs/2505.22543v1 |
a comprehensive assessment. The requirements are as follows: if any of the five descriptions contain at least one meaning that is equivalent to or closely to 'the video does not play smoothly and experiences stuttering', then the final summary should be based solely on these descriptions. Additionally, please assign a ... | https://arxiv.org/abs/2505.22543v1 |
{key} of the video: {annotation[key][5]} (Please note that if the description is related to the 'flicker' of the video, the term 'flicker' here refers solely to 'frame shake/camera shake' and carries no additional meaning.). Please carefully observe the keyframe especially on the {key} aspect) and assess whether you ag... | https://arxiv.org/abs/2505.22543v1 |
branch (2). Step 2: Instruction Pairs Generation (for openended） System Prompt:"""You will receive a detailed description of the quality of a video regarding to 8 quality factors of the video: sharpness, light, compression_artifact, fluency, flickers, color, motion blur and noise (Please note that the term 'flicker' he... | https://arxiv.org/abs/2505.22543v1 |
2: Question: How is the flicker condition when the scene switches to the playground? A.Very severe B.Noticeable C.Mild D.Does not exist. Answer: B.Noticeable." + " Question 3: Question: How is the sharpness throughout the video playback? Answer: Due to compression blur present throughout the video, the sharpness is rel... | https://arxiv.org/abs/2505.22543v1 |
distortion in the video. 2. Ask and answer the location of the spatiotemporal local distortion within the video frame. If only a general description of the location is provided (such as center, top left, bottom right, etc.), answer with a location description. If the description contains specific semantic objects about... | https://arxiv.org/abs/2505.22543v1 |
not only include the emotional feedback arising from its content or artistic style, but also consider the comfort level of its presentation. For example, videos with excessive flickering or rapid scene transitions may cause dizziness and discomfort, while videos with stable scene transitions and well-composed shots ten... | https://arxiv.org/abs/2505.22543v1 |
is quite clear.", "Compression artifacts are noticeable, particularly in detailed areas like character outlines and background elements, ranging from mild to severe blockiness .", "2 points. ,"2 points,"2 points ], "flickers" : [ "The flicker is noticeable throughout the video." , "There is a slight flicker throughout ... | https://arxiv.org/abs/2505.22543v1 |
persistent camera shake is noticeable. Colors appear slightly muted with a neutral tone and consistent brightness. Significant motion blur, resulting in ghosting artifacts, is apparent, particularly during movement. The video also suffers from a noticeable level of noise. "quality Q1": "Question: How does the lighting ... | https://arxiv.org/abs/2505.22543v1 |
block effects and significant blur." , "The compression artifact is noticeable in the video, with a significant loss of edge detail." , "The video has severe compression artifacts, with noticeable block effects in the text areas." , "The compression artifacts in the video are severe, with noticeable block effects." , "... | https://arxiv.org/abs/2505.22543v1 |
"There is a small amount of noise in the video." , "The video exhibits a moderate level of noise.", "2 points.","2 points.","2 points."] Step3:Instruction Pairs Generation "overall_annotation": "This video suffers from inconsistent lighting, with overexposed foregrounds and underexposed backgrounds. Significant compres... | https://arxiv.org/abs/2505.22543v1 |
some details, such as ground tiles, appear slightly soft.", "2 points.","2 points.","2 points." ], "light": [ "The light is relatively uniform, with no overexposure or underexposure issues." , "The video is bright throughout its playback." , "The overall light of the video is relatively dark." , "The light is moderate ... | https://arxiv.org/abs/2505.22543v1 |
"The video suffers from noticeable compression artifacts, particularly evident as blockiness .", "2 points.","2 points.","2 points." ], "fluency" : [ "The video playback is smooth and fluent, with no stuttering." , "The video is smooth." , "The video is fairly fluent throughout." , "The video plays smoothly and fluentl... | https://arxiv.org/abs/2505.22543v1 |
impacted by the aforementioned motion blur and compression artifacts.."},Video Input Figure 17. Technical branch annotation example(3). aesthetic branch Annotation Example 1 "video_name": "HIGHQUALITY/ia-batch14_bctvnh-Around_Town_with_Dianne_Bzik_-_Miss_Bedford_Scholarship_Program.mp4", "aesthetic_description": "1. Ov... | https://arxiv.org/abs/2505.22543v1 |
is comfortable, avoiding extreme close-ups or awkward angles. The spatial aesthetic aligns with the informational nature of the presumed interview.\n\n b. **Temporal:** The provided keyframes suggest a static shot with no camera movement. There is no discernible change in the spatial aesthetic over the shown duration.\... | https://arxiv.org/abs/2505.22543v1 |
B. Simple and Documentary-style. The clear, wide-angle views and straightforward composition prioritize conveying information about the location in a direct and functional manner.", "aesthetic Q5": "Please give the detailed description of the aesthetic effects of the video. Answer:1. **Overall Aesthetic Style:** The vi... | https://arxiv.org/abs/2505.22543v1 |
you will see a sequence of images generated by uniformly sampling 1 frame per second from the video. The image sequence follows the original order of the video. After uniform sampling, there are a total of 4 images:\n <image>. In addition, you will also obtain motion features extracted from all 148 frames of the the en... | https://arxiv.org/abs/2505.22543v1 |
C. Lower right corner, D. Lower left portion of the torso and left arm \n Answer: D. Lower left portion of the torso and left arm", "incontext Q3": "(Open-ended): \nQuestion: What specific distortion occurs on the left arm and the lower left portion of the torso, and how severe is it? Answer: Severe compression.", "inc... | https://arxiv.org/abs/2505.22543v1 |
only [Answer 1] and [Answer 2] need to be filled; for Multi-choice (single-answer) type questions, all four answer options should be filled in; and for Open-ended questions, only [Answer 1] is required. The [Correct Answer] is a drop-down menu where the annotator selects the correct option. Each question has correspond... | https://arxiv.org/abs/2505.22543v1 |
second, severe camera shake and motion blur suddenly occur. This example demonstrates that OmniVQA-Chatter possesses accurate temporal distortion localization (precise to the second)and is highly sensitive to temporal retrieval of specific distortions. Figure 27. This video was recorded using a professional camera with... | https://arxiv.org/abs/2505.22543v1 |
arXiv:2505.22552v1 [cs.CL] 28 May 2025ClaimPKG: Enhancing Claim Verification via Pseudo-Subgraph Generation with Lightweight Specialized LLM Hoang Pham*, Thanh-Do Nguyen*, Khac-Hoai Nam Bui† Viettel Artificial Intelligence and Data Services Center, Viettel Group, Vietnam {hoangpv4, dont15, nambkh}@viettel.com.vn Abstra... | https://arxiv.org/abs/2505.22552v1 |
limited. Existing KG- based approaches (Figure 1(b)) (Kim et al., 2023b; Zhou et al., 2019; Kim et al., 2023a) lack end-to- end solutions, often requiring pre-extracted entities via modules like entity or relation extraction. Mean- while, despite excelling at general reasoning, LLMs struggle with KG-specific tasks like... | https://arxiv.org/abs/2505.22552v1 |
work developing specialized architec- tures: graph neural networks for knowledge graph processing (Zhou et al., 2020), table-specific trans- formers (Herzig et al., 2020), and tree-structured decoders for hierarchical data (Wang et al., 2020). Claim Verification over Knowledge Graphs (KGs). The emergence of Large Langu... | https://arxiv.org/abs/2505.22552v1 |
textual claim c, andpθ(Sc|Pc,G) models the distribution over relevant subgraphs Sc givenPc. While equations 1 and 2 establish our theoretical framework for ClaimPKG, computing exact probabilities by summing over all possible (Sc,Pc)pairs is intractable. Addressing this we propose two approximations: (1) We infer the ve... | https://arxiv.org/abs/2505.22552v1 |
verify a claim is to understand its content thoroughly and represent it in a format compatible with the KG. Since evi- dence comes from KG, representing claims in the graph format is crucial, which captures hypotheti- cal relations among entities in an effective way that enables effective comparisons with KG subgraphs ... | https://arxiv.org/abs/2505.22552v1 |
greater similarity. This function can be instantiated via various mechanisms (e.g., embedding similarity, re-ranking, fuzzy matching, etc.). Incomplete Triplets Retrieval: Our goal is to identify evidence (actual triplets in the KG) to in- form us about entities marked as unknown and their respective relations with exp... | https://arxiv.org/abs/2505.22552v1 |
the ClaimPKG framework by determining claim ve- racity through reasoning over input claim cand retrieved evidence subgraph S∗ c. As complex tasks, especially claim verification, require deliber- ate chain-of-thought reasoning (Jiang et al., 2020; Wang et al., 2023), we use a general-purpose LLM to analyze candS∗ c. Usi... | https://arxiv.org/abs/2505.22552v1 |
for the Relation Scoring Function, we set the primary hyperparameters to k1= 3andk2= 1. Detailed justification is provided in Appendix C. 5.2 Results and Analysis We present the main experimental results in this section and additional findings in Appendix C. (RQ1): How Does ClaimPKG Perform Against the Baselines? Table... | https://arxiv.org/abs/2505.22552v1 |
Retrieval. Removing the Incomplete Triplet Retrieval function, which forces the re- trieval algorithm to only query evidence using com- plete triplets, causes a significant average perfor- mance drop of nearly 20% compared to the full setup, showing the complete graph structure of in- put claims is essential for optima... | https://arxiv.org/abs/2505.22552v1 |
specialized LLM and keep the General LLM to be Llama-3.3-70B. We evaluate perfor- mance based on two metrics: average accuracy on the test set and claim structure coverage on the dev set. As shown in Figure 3, the Specialized LLMs achieve satisfactory accuracy (Llama-3.2- 3B: 79.35%, Qwen-2.5-3B: 77.62%) with just 100 ... | https://arxiv.org/abs/2505.22552v1 |
components to handle this type of information is crucial. Another limitation is the performance decline observed when the Specialized LLM is trained on an excessive number of examples, high- lighting the need for future research into regular- ization strategies. Further improvements should also focus on the general rea... | https://arxiv.org/abs/2505.22552v1 |
Toronto, Canada, July 9-14, 2023 , pages 16190–16206. Association for Computa- tional Linguistics. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. Effi- cient memory management for large language model serving with pagedattention. In P... | https://arxiv.org/abs/2505.22552v1 |
COLING 2018, Santa Fe, New Mexico, USA, August 20-26, 2018 , pages 3346–3359. Association for Computa- tional Linguistics. James Thorne, Andreas Vlachos, Christos Christodoulopoulos, and Arpit Mittal. 2018. FEVER: a large-scale dataset for fact extraction and verification. In Proceedings of the 2018 Conference of the N... | https://arxiv.org/abs/2505.22552v1 |
1,340 12,466 1,807 15,613 Total 34,462 64,788 9,424 108,674 Table 5: Dataset statistics of FACTKG for claim types. FEVEROUS. (Aly et al., 2021) FEVEROUS is a fact verification dataset comprising 87,026 veri- fied claims sourced from Wikipedia (Table 4). Each claim is accompanied by evidence in the form of sentences and... | https://arxiv.org/abs/2505.22552v1 |
is Post-metal, played with the band Twilight and performs for Mamiffer. Entities: [Mamiffer, Post-metal, Twilight_(band)] Evidence: - Twilight_(band), ( associatedMusicalArtist, associated- Band), Mamiffer) - Twilight_(band), ( associatedMusicalArtist, genre), Post- metal Figure 4: Provided data of FactKG Preprocessing... | https://arxiv.org/abs/2505.22552v1 |
graph Retrieval by adjusting the hyperparameters k1andk2as explained in the 4.3, which influence the diversity and correctness of the retrieved sub- graphs. C.1 Metrics The specialized LLM’s generation of pseudo- subgraphs plays a crucial role in ClaimPKG’s per- formance. We evaluated the specialized LLM’s per- formanc... | https://arxiv.org/abs/2505.22552v1 |
Different Model Sizes of the Specialized LLM To evaluate how model size affects performance, we compare different variants of Llama and Qwen models ranging from 1B to 8B parameters. Ta- ble 9 presents the performance on the FactKG dev set across three key metrics: average performance, structure coverage, and unique tri... | https://arxiv.org/abs/2505.22552v1 |
tion and evaluate the test set of FactKG while fix the Specialized LLM and the General LLM. Specif- ically, we explore multiple strategies for the Rela- tion Scoring Function ( Sim), as described in Sec- tion 4.3, incorporating diverse techniques such as embedding-based retrieval, reranking, fuzzy text matching (Wikipe... | https://arxiv.org/abs/2505.22552v1 |
ifnew_token == EOS then break ; return P GENERAL REASONING Task: Verify whether the fact in the given sentence is true or false based on the provided graph triplets. Use only the information in the triplets for verification. - The triplets provided represent all relevant knowledge that can be retrieved. - If the fact i... | https://arxiv.org/abs/2505.22552v1 |
|| Pennsylvania P4:11th Mississippi Infantry Monument || is part of military conflict || Gettysburg 11th Mississippi Infantry Monument || location || Pennsylvania 11th Mississippi Infantry Monument || ~location || unknown_0 P5:11th Mississippi Infantry Monument || location || Gettysburg, Pennsylvania(11th Mississippi I... | https://arxiv.org/abs/2505.22552v1 |
(County of Tyrol, ~birth place, Kurt Schuschnigg) (County of Tyrol, ~birth place, Alfons Gorbach) (County of Tyrol, ~birth place, Josef Hellensteiner) (Kurt Schuschnigg, death place, Austria) (Alfons Gorbach, death place, Austria) (Josef Hellensteiner, death place, Austria) (Barbara Prammer, successor, Doris Bures) (We... | https://arxiv.org/abs/2505.22552v1 |
in the Cape Verde whose capital was Winch- ester.P1:Cape Verde || capital || Winchester Cape Verde || ~residence || Lady Anne Monson P2: Lady Anne Monson || residence || Cape Verde Cape Verde || capital || Winchester P3:Anne Monzon || residence || Cape Verde Cape Verde || capital || Winchester P4:Cape Verde || capital ... | https://arxiv.org/abs/2505.22552v1 |
length, Agra Airport) (1818.0, runway length, Agra Airport) (HAL Light Combat Helicopter, aircraft helicopter, Indian Air Force) (HAL Light Combat Helicopter, aircraft attack, Army Aviation Corps (India)) (HAL Light Combat Helicopter, type, Attack heli- copter) (Agra Airport, icao location identifier, VIAG) (Airlift, t... | https://arxiv.org/abs/2505.22552v1 |
arXiv:2505.22564v1 [cs.CV] 28 May 2025PRISM: Video Dataset Condensation with Progressive Refinement and Insertion for Sparse Motion Jaehyun Choi Jiwan Hur Gyojin Han Jaemyung Yu Junmo Kim Korea Advanced Institute of Science and Technology (KAIST) {chlwogus, jiwan.hur, hangj0820, jaemyung, junmo.kim}@kaist.ac.kr Abstrac... | https://arxiv.org/abs/2505.22564v1 |
Update Gradient (Per−Frame ) Optimizable Frame One−step optimized FrameFigure 1: Visual representation of prior video dataset condensation methods and PRISM (Ours). In frame-wise matching, each frame gets updated individually, neglecting the relation between one another. Static and dynamic disentangling method [ 11] le... | https://arxiv.org/abs/2505.22564v1 |
original dataset. DC [ 9] pioneered this direction by formulating dataset distillation as a bi-level optimization problem that matches single-step gradients between original and synthetic datasets. DSA [ 14] enhanced this framework through differentiable Siamese augmentation, improving generalization by ensuring consis... | https://arxiv.org/abs/2505.22564v1 |
the video segment, rather than the entire sequence of T 3 Interpolated Frame Interpolation between two framesMatching Loss (ℒ 𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚 ) Start Frame End Frame Video Dataset Optimizable Frame∇𝑠𝑠𝑐𝑐,𝑘𝑘𝑖𝑖 ℒ𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑠𝑠𝑚𝑚,𝑘𝑘𝑖𝑖∇𝑠𝑠𝑐𝑐,1 ℒ𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑚𝑠𝑠𝑚𝑚,1∇𝑠𝑠𝑐𝑐,𝑇𝑇 ℒ𝑚𝑚𝑚𝑚... | https://arxiv.org/abs/2505.22564v1 |
increasing along every such direction. Therefore, stmust be promoted to the key-frame set and directly optimized to enable further loss minimization. Proof. See supplementary material A. □ 3.3 Warm-Up and Cool-Down Scheduling To ensure stable optimization and avoid the premature or unstable expansion of the key frame s... | https://arxiv.org/abs/2505.22564v1 |
6.3±0.2 2.8±0.1 3.6±0.1 K-Center [23] 13.9±1.623.2±0.729.1±0.62.4±0.4 5.2±0.4 8.0±0.1 3.1±0.1 6.2±0.2 2.6±0.2 4.5±0.1 Static / Dynamic Disentangled Methods DM [12] 15.3±1.125.7±0.230.0±0.66.1±0.2 8.0±0.2 12.1±0.46.3±0.0 9.1±0.9 3.6±0.0 4.1±0.0 + Wang et al.†[11] 17.5 ±0.127.2±0.4 - 6.0±0.4 8.2±0.1 - 6.3 ±0.2 7.0±0.1 4.... | https://arxiv.org/abs/2505.22564v1 |
under different VPC settings.† represents the author provided results. Dataset MiniUCF HMDB51 VPC 1 5 10 1 5 10 Coreset Methods Random 115 586 1.15GB 115 586 1.17GB Herding [22] 115 586 1.15GB 115 586 1.17GB K-Center [23] 115 586 1.15GB 115 586 1.17GB Disentangled Methods DM [12] 115 586 586 115 586 586 + Wang et al.†[... | https://arxiv.org/abs/2505.22564v1 |
the best scores for each dataset. DatasetNumber of Initial Key Frames 2 3 4 6 8 MiniUCF 17.9±0.3 16.4±0.5 15.9±0.3 15.0±0.2 14.8±0.2 HMDB51 7.5±0.3 6.4±0.2 6.0±0.4 5.2±0.4 4.9±0.2 Table 5: Ablation study results for (A) with and without insertion, (B) frame selection strategy, (C) similarity metric, and (D) training ph... | https://arxiv.org/abs/2505.22564v1 |
cosine similarity is truly essential, we compare it against a distance-based alternative using the L2 norm. However, unlike cosine similarity, which has a well- defined geometric interpretation (e.g., zero for orthogonal gradients), L2 distance lacks a natural threshold. To make the comparison meaningful, we calibrated... | https://arxiv.org/abs/2505.22564v1 |
misalignment, particularly early in training when gradients are noisy. Second, when applied to very long video sequences, the initial frame optimization from Gaussian noise may become unstable. This resembles difficulties observed in long-range video generation, where spatiotemporal consistency becomes harder to preser... | https://arxiv.org/abs/2505.22564v1 |
on Computer Vision and Pattern Recognition , 2024, pp. 6296–6304. [12] B. Zhao and H. Bilen, “Dataset condensation with distribution matching,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision , 2023, pp. 6514–6523. [13] G. Cazenavette, T. Wang, A. Torralba, A. A. Efros, and J.-Y . Zh... | https://arxiv.org/abs/2505.22564v1 |
By the bilinearity of the inner product, ⟨gt, v⟩=λ⟨gt,−gi⟩+ (1−λ)⟨gt,−gi+1⟩. Applying the assumption ⟨gt, gi⟩<0, we obtain ⟨gt,−gi⟩=−⟨gt, gi⟩>0, and similarly, ⟨gt,−gi+1⟩=−⟨gt, gi+1⟩>0. Therefore, ⟨gt, v⟩=λ· ⟨gt,−gi⟩+ (1−λ)· ⟨gt,−gi+1⟩>0. This shows that the directional derivative of Latstalong any direction vformed by... | https://arxiv.org/abs/2505.22564v1 |
abrupt motions, the resulting flow fields from the condensed video occasionally lack directional consistency and show spatial noise, indicating poor alignment. These limitations appear to be exacerbated by the use of Gaussian noise initialization, which may hinder the model’s ability to focus solely on the informative ... | https://arxiv.org/abs/2505.22564v1 |
arXiv:2505.22566v1 [cs.CV] 28 May 2025Universal Visuo-Tactile Video Understanding for Embodied Interaction Yifan Xie1, Mingyang Li1, Shoujie Li1, Xingting Li1, Guangyu Chen2, Fei Ma3, Fei Richard Yu3, Wenbo Ding1 1Tsinghua University 2Sun Yat-sen University 3Guangdong Laboratory of Artificial Intelligence and Digital E... | https://arxiv.org/abs/2505.22566v1 |
Distinction velvet.mp4Question: Describe these two videos based on their tactile attributes: a) <bark.mp4> , b) <velvet.mp4> . Which material would be better for lining the inside of a box meant to hold delicate jewelry ?VTV-LLM: a) It presents a extremely hard and strong protrusion surface with no elasticity and stron... | https://arxiv.org/abs/2505.22566v1 |
language interaction. •We contribute VTV150K, a comprehensive dataset of 150,000 visuo-tactile video frames capturing 100 diverse objects across three tactile sensors, annotated with four fundamental tactile attributes. •We develop a novel three-stage training paradigm that effectively bridges the domain gap between ta... | https://arxiv.org/abs/2505.22566v1 |
language. 3 3 Methods In this section, we first introduce VTV150K, a large-scale dataset of video-question-answer pairs in Sec. 3.1. Subsequently, we present VTV-LLM, the first visuo-tactile video large language model designed for visuo-tactile video understanding and embodied interaction in Sec. 3.2. 3.1 VTV150K Overv... | https://arxiv.org/abs/2505.22566v1 |
the Supplementary Material. 3.2 VTV-LLM Overview VTV-LLM aims to serve as a multi-modal framework capable of integrating visual- tactile video data with large language models to facilitate tactile reasoning for embodied interaction. As illustrated in Fig. 2(a), VTV-LLM formulates tactile perception as a cross-modal app... | https://arxiv.org/abs/2505.22566v1 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.