Promoting products for kids? Explore channels in 'Kids & Parenting' and 'Psychology & Relationships' topics.

28.4

Advertising on the Telegram channel «Data Science | Machine Learning for Researchers»

Computer science

Language:

English

The Data Science and Python channel is for researchers and advanced programmers

Share

Add to favorite

Buy advertising in this channel

Placement Format:

keyboard_arrow_down

1/24
2/48
3/72
Native
7 days
Forwards

1 hour in the top / 24 hours in the feed

Quantity

keyboard_arrow_down

1
2
3
4
5
8
10
15

Advertising publication cost

$6.00

$6.00

Recent Channel Posts

Article Title: OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data Article Date: 24 May 2025 Article Description: Diffusion models have advanced image stylization significantly, yet two core challenges persist: (1) maintaining consistent stylization in complex scenes, particularly identity, composition, and fine details, and (2) preventing style degradation in image-to-image pipelines with style LoRAs. GPT-4o's exceptional stylization consistency highlights the performance gap between open-source methods and proprietary models. To bridge this gap, we propose \textbf{OmniConsistency}, a universal consistency plugin leveraging large-scale Diffusion Transformers (DiTs). OmniConsistency contributes: (1) an in-context consistency learning framework trained on aligned image pairs for robust generalization; (2) a two-stage progressive learning strategy decoupling style learning from consistency preservation to mitigate style degradation; and (3) a fully plug-and-play design compatible with arbitrary style LoRAs under the Flux framework. Extensive experiments show that OmniConsistency significantly enhances visual coherence and aesthetic quality, achieving performance comparable to commercial state-of-the-art model GPT-4o.PDFAbstract PDF Download Link: https://arxiv.org/pdf/2505.18445v1.pdf GitHub: • https://github.com/showlab/omniconsistency Datasets: • No datasets information available ================================== For more data science resources: ✓ https://t.me/DataScienceT

125

13:58

06.06.2025

Article Title: ImgEdit: A Unified Image Editing Dataset and Benchmark Article Date: 26 May 2025 Article Description: Recent advancements in generative models have enabled high-fidelity text-to-image generation. However, open-source image-editing models still lag behind their proprietary counterparts, primarily due to limited high-quality data and insufficient benchmarks. To overcome these limitations, we introduce ImgEdit, a large-scale, high-quality image-editing dataset comprising 1.2 million carefully curated edit pairs, which contain both novel and complex single-turn edits, as well as challenging multi-turn tasks. To ensure the data quality, we employ a multi-stage pipeline that integrates a cutting-edge vision-language model, a detection model, a segmentation model, alongside task-specific in-painting procedures and strict post-processing. ImgEdit surpasses existing datasets in both task novelty and data quality. Using ImgEdit, we train ImgEdit-E1, an editing model using Vision Language Model to process the reference image and editing prompt, which outperforms existing open-source models on multiple tasks, highlighting the value of ImgEdit and model design. For comprehensive evaluation, we introduce ImgEdit-Bench, a benchmark designed to evaluate image editing performance in terms of instruction adherence, editing quality, and detail preservation. It includes a basic testsuite, a challenging single-turn suite, and a dedicated multi-turn suite. We evaluate both open-source and proprietary models, as well as ImgEdit-E1, providing deep analysis and actionable insights into the current behavior of image-editing models. The source data are publicly available on https://github.com/PKU-YuanGroup/ImgEdit.PDFAbstract PDF Download Link: https://arxiv.org/pdf/2505.20275v1.pdf GitHub: • https://github.com/pku-yuangroup/imgedit Datasets: • MagicBrush ================================== For more data science resources: ✓ https://t.me/DataScienceT

446

04:23

06.06.2025

Article Title: MTGS: Multi-Traversal Gaussian Splatting Article Date: 16 Mar 2025 Article Description: Multi-traversal data, commonly collected through daily commutes or by self-driving fleets, provides multiple viewpoints for scene reconstruction within a road block. This data offers significant potential for high-quality novel view synthesis, which is crucial for applications such as autonomous vehicle simulators. However, inherent challenges in multi-traversal data often result in suboptimal reconstruction quality, including variations in appearance and the presence of dynamic objects. To address these issues, we propose Multi-Traversal Gaussian Splatting (MTGS), a novel approach that reconstructs high-quality driving scenes from arbitrarily collected multi-traversal data by modeling a shared static geometry while separately handling dynamic elements and appearance variations. Our method employs a multi-traversal dynamic scene graph with a shared static node and traversal-specific dynamic nodes, complemented by color correction nodes with learnable spherical harmonics coefficient residuals. This approach enables high-fidelity novel view synthesis and provides flexibility to navigate any viewpoint. We conduct extensive experiments on a large-scale driving dataset, nuPlan, with multi-traversal data. Our results demonstrate that MTGS improves LPIPS by 23.5% and geometry accuracy by 46.3% compared to single-traversal baselines. The code and data would be available to the public.PDFAbstract PDF Download Link: https://arxiv.org/pdf/2503.12552v3.pdf GitHub: • https://github.com/OpenDriveLab/MTGS Datasets: • No datasets information available ================================== For more data science resources: ✓ https://t.me/DataScienceT

645

14:14

05.06.2025

Article Title: Harnessing the Universal Geometry of Embeddings Article Date: 18 May 2025 Article Description: We introduce the first method for translating text embeddings from one vector space to another without any paired data, encoders, or predefined sets of matches. Our unsupervised approach translates any embedding to and from a universal latent representation (i.e., a universal semantic structure conjectured by the Platonic Representation Hypothesis). Our translations achieve high cosine similarity across model pairs with different architectures, parameter counts, and training datasets. The ability to translate unknown embeddings into a different space while preserving their geometry has serious implications for the security of vector databases. An adversary with access only to embedding vectors can extract sensitive information about the underlying documents, sufficient for classification and attribute inference.PDFAbstract PDF Download Link: https://arxiv.org/pdf/2505.12540v2.pdf GitHub: • https://github.com/rjha18/vec2vec • https://github.com/zhaoolee/garss Datasets: • Natural Questions ================================== For more data science resources: ✓ https://t.me/DataScienceT

701

05:33

05.06.2025

Article Title: Vision as LoRA Article Date: 26 Mar 2025 Article Description: We introduce Vision as LoRA (VoRA), a novel paradigm for transforming an LLM into an MLLM. Unlike prevalent MLLM architectures that rely on external vision modules for vision encoding, VoRA internalizes visual capabilities by integrating vision-specific LoRA layers directly into the LLM. This design allows the added parameters to be seamlessly merged into the LLM during inference, eliminating structural complexity and minimizing computational overhead. Moreover, inheriting the LLM's ability of handling flexible context, VoRA can process inputs at arbitrary resolutions. To further strengthen VoRA's visual capabilities, we introduce a block-wise distillation method that transfers visual priors from a pre-trained ViT into the LoRA layers, effectively accelerating training by injecting visual knowledge. Additionally, we apply bi-directional attention masks to better capture the context information of an image. We successfully demonstrate that with additional pre-training data, VoRA can perform comparably with conventional encode-based MLLMs. All training data, codes, and model weights will be released at https://github.com/Hon-Wong/VoRA.PDFAbstract PDF Download Link: https://arxiv.org/pdf/2503.20680v1.pdf GitHub: • https://github.com/hon-wong/vora Datasets: • MM-Vet • Google Landmarks Dataset v2 ================================== For more data science resources: ✓ https://t.me/DataScienceT

824

13:39

04.06.2025

Update Telegram, now job seekers can advertise their expertise and job opportunities without having to go back to the channel owner

792

07:30

04.06.2025

Article Title: s3: You Don't Need That Much Data to Train a Search Agent via RL Article Date: 20 May 2025 Article Description: Retrieval-augmented generation (RAG) systems empower large language models (LLMs) to access external knowledge during inference. Recent advances have enabled LLMs to act as search agents via reinforcement learning (RL), improving information acquisition through multi-turn interactions with retrieval engines. However, existing approaches either optimize retrieval using search-only metrics (e.g., NDCG) that ignore downstream utility or fine-tune the entire LLM to jointly reason and retrieve-entangling retrieval with generation and limiting the real search utility and compatibility with frozen or proprietary models. In this work, we propose s3, a lightweight, model-agnostic framework that decouples the searcher from the generator and trains the searcher using a Gain Beyond RAG reward: the improvement in generation accuracy over naive RAG. s3 requires only 2.4k training samples to outperform baselines trained on over 70x more data, consistently delivering stronger downstream performance across six general QA and five medical QA benchmarks.PDFAbstract PDF Download Link: https://arxiv.org/pdf/2505.14146v1.pdf GitHub: • https://github.com/pat-jj/s3 Datasets: • Natural Questions • TriviaQA • HotpotQA • MedQA • PubMedQA ================================== For more data science resources: ✓ https://t.me/DataScienceT

825

06:39

04.06.2025

Article Title: Uncertainty Quantification for Language Models: A Suite of Black-Box, White-Box, LLM Judge, and Ensemble Scorers Article Date: 27 Apr 2025 Article Description: Hallucinations are a persistent problem with Large Language Models (LLMs). As these models become increasingly used in high-stakes domains, such as healthcare and finance, the need for effective hallucination detection is crucial. To this end, we propose a versatile framework for zero-resource hallucination detection that practitioners can apply to real-world use cases. To achieve this, we adapt a variety of existing uncertainty quantification (UQ) techniques, including black-box UQ, white-box UQ, and LLM-as-a-Judge, transforming them as necessary into standardized response-level confidence scores ranging from 0 to 1. To enhance flexibility, we introduce a tunable ensemble approach that incorporates any combination of the individual confidence scores. This approach enables practitioners to optimize the ensemble for a specific use case for improved performance. To streamline implementation, the full suite of scorers is offered in this paper's companion Python toolkit, UQLM. To evaluate the performance of the various scorers, we conduct an extensive set of experiments using several LLM question-answering benchmarks. We find that our tunable ensemble typically surpasses its individual components and outperforms existing hallucination detection methods. Our results demonstrate the benefits of customized hallucination detection strategies for improving the accuracy and reliability of LLMs.PDFAbstract PDF Download Link: https://arxiv.org/pdf/2504.19254v2.pdf GitHub: • https://github.com/cvs-health/uqlm Datasets: • GSM8K • SVAMP • PopQA ================================== For more data science resources: ✓ https://t.me/DataScienceT

892

14:04

03.06.2025

Article Title: Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video Article Date: 27 Mar 2025 Article Description: This paper presents a unified approach to understanding dynamic scenes from casual videos. Large pretrained vision foundation models, such as vision-language, video depth prediction, motion tracking, and segmentation models, offer promising capabilities. However, training a single model for comprehensive 4D understanding remains challenging. We introduce Uni4D, a multi-stage optimization framework that harnesses multiple pretrained models to advance dynamic 3D modeling, including static/dynamic reconstruction, camera pose estimation, and dense 3D motion tracking. Our results show state-of-the-art performance in dynamic 4D modeling with superior visual quality. Notably, Uni4D requires no retraining or fine-tuning, highlighting the effectiveness of repurposing visual foundation models for 4D understanding.PDFAbstract PDF Download Link: https://arxiv.org/pdf/2503.21761v1.pdf GitHub: • https://github.com/Davidyao99/uni4d Datasets: • KITTI • DAVIS • TUM RGB-D • MPI Sintel • Bonn RGB-D Dynamic ================================== For more data science resources: ✓ https://t.me/DataScienceT

888

04:17

03.06.2025

Article Title: VITA-Audio: Fast Interleaved Cross-Modal Token Generation for Efficient Large Speech-Language Model Article Date: 6 May 2025 Article Description: With the growing requirement for natural human-computer interaction, speech-based systems receive increasing attention as speech is one of the most common forms of daily communication. However, the existing speech models still experience high latency when generating the first audio token during streaming, which poses a significant bottleneck for deployment. To address this issue, we propose VITA-Audio, an end-to-end large speech model with fast audio-text token generation. Specifically, we introduce a lightweight Multiple Cross-modal Token Prediction (MCTP) module that efficiently generates multiple audio tokens within a single model forward pass, which not only accelerates the inference but also significantly reduces the latency for generating the first audio in streaming scenarios. In addition, a four-stage progressive training strategy is explored to achieve model acceleration with minimal loss of speech quality. To our knowledge, VITA-Audio is the first multi-modal large language model capable of generating audio output during the first forward pass, enabling real-time conversational capabilities with minimal latency. VITA-Audio is fully reproducible and is trained on open-source data only. Experimental results demonstrate that our model achieves an inference speedup of 3~5x at the 7B parameter scale, but also significantly outperforms open-source models of similar model size on multiple benchmarks for automatic speech recognition (ASR), text-to-speech (TTS), and spoken question answering (SQA) tasks.PDFAbstract PDF Download Link: https://arxiv.org/pdf/2505.03739v1.pdf GitHub: • https://github.com/vita-mllm/vita-audio Datasets: • LibriSpeech • TriviaQA • LibriTTS • AISHELL-1 • FLEURS • VoxPopuli • LIMA • GigaSpeech • Multilingual LibriSpeech • AISHELL-2 • WenetSpeech • MathInstruct ================================== For more data science resources: ✓ https://t.me/DataScienceT

887

15:59

02.06.2025

close

Reviews channel

keyboard_arrow_down

Added: Newest first
Added: Oldest first
Rating: High to low
Rating: Low to high

4.6

2 reviews over 6 months

Excellent (50%) In the last 6 months

Very good (50%) In the last 6 months

Everything is fine. Thank you!

Show more

New items

17.6

چهارراه کامپیوتر

Computer science

33.4K

ER:

8.7%

$24.00

$24.00

17.5

Et21 Crypto Net

Computer science

2.2K

ER:

62.3%

$1.20

$1.20

17.5

Tech Psyche . Tech Tips & Tricks . Programming , Tech Courses

Computer science

2.0K

ER:

--

$1.20

$1.20

17.5

FREE INTERNET SERVER 🇪🇹

Computer science

6.6K

ER:

16.0%

$2.40

$2.40

17.4

ETHIOPIA FREE INTERNAT AND 𝐄THIOPIA 𝐂𝐑𝐘𝐏𝐓𝐎™️

Computer science

2.2K

ER:

27.5%

$1.20

$1.20

17.4

𝕿𝖊𝖈𝖍 𝕳𝖚𝖇 𝕶𝖊𝖓𝖞𝖆

Computer science

2.9K

ER:

19.6%

$1.20

$1.20

17.4

ZUSYCO-DB

Computer science

2.2K

ER:

--

$1.20

$1.20

17.4

Ethio unlimited

Computer science

2.5K

ER:

65.2%

$3.60

$3.60

17.2

Liza Mods

Computer science

9

ER:

187.5%

$54.00

$54.00

16.5

NIGUS ZONE

Computer science

4.5K

ER:

8.7%

$1.20

$1.20

15.4

ETHIOPIAN UNLIMITED🇪🇹

Computer science

2.1K

ER:

22.0%

$1.56

$1.56

13.5

Y_Tech

Computer science

1.8K

ER:

34.0%

$1.20

$1.20

12.5

Almighty Tech

Computer science

20.6K

ER:

--

$12.00

$12.00

12.5

🧠 AI Toolbox Daily

Computer science

4.3K

ER:

--

$4.80

$4.80

12.4

FREE INTERNET

Computer science

4.3K

ER:

--

$1.20

$1.20

Channel statistics

Rating

28.4

Rating reviews

4.6

Сhannel Rating

83

Selected

0

channels for:

$0.00

Subscribers:

0

Views:

Add to CartBuy for:$0.00

Sign up

Password Recovery

Log in