ML Research Hub
32.8K subscribers
4.3K photos
260 videos
23 files
4.65K links
Advancing research in Machine Learning – practical insights, tools, and techniques for researchers.

Admin: @HusseinSheikho || @Hussein_Sheikho
Download Telegram
πŸ”Ή Title: PRISM-Bench: A Benchmark of Puzzle-Based Visual Tasks with CoT Error Detection

πŸ”Ή Publication Date: Published on Oct 27

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.23594
β€’ PDF: https://arxiv.org/pdf/2510.23594
β€’ Github: https://github.com/JornyWan/PRISM-Bench

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: ReCode: Unify Plan and Action for Universal Granularity Control

πŸ”Ή Publication Date: Published on Oct 27

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.23564
β€’ PDF: https://arxiv.org/pdf/2510.23564

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Knocking-Heads Attention

πŸ”Ή Publication Date: Published on Oct 27

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.23052
β€’ PDF: https://arxiv.org/pdf/2510.23052

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: LightBagel: A Light-weighted, Double Fusion Framework for Unified Multimodal Understanding and Generation

πŸ”Ή Publication Date: Published on Oct 27

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.22946
β€’ PDF: https://arxiv.org/pdf/2510.22946
β€’ Project Page: https://ucsc-vlaa.github.io/LightBagel/

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: LongCat-Video Technical Report

πŸ”Ή Publication Date: Published on Oct 25

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.22200
β€’ PDF: https://arxiv.org/pdf/2510.22200
β€’ Github: https://github.com/meituan-longcat/LongCat-Video

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation

πŸ”Ή Publication Date: Published on Oct 27

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.23581
β€’ PDF: https://arxiv.org/pdf/2510.23581
β€’ Project Page: https://lookahead-anchoring.github.io/
β€’ Github: https://lookahead-anchoring.github.io/

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Track, Inpaint, Resplat: Subject-driven 3D and 4D Generation with Progressive Texture Infilling

πŸ”Ή Publication Date: Published on Oct 27

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.23605
β€’ PDF: https://arxiv.org/pdf/2510.23605

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: VoMP: Predicting Volumetric Mechanical Property Fields

πŸ”Ή Publication Date: Published on Oct 27

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.22975
β€’ PDF: https://arxiv.org/pdf/2510.22975
β€’ Project Page: https://research.nvidia.com/labs/sil/projects/vomp

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: A Survey of Data Agents: Emerging Paradigm or Overstated Hype?

πŸ”Ή Publication Date: Published on Oct 27

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.23587
β€’ PDF: https://arxiv.org/pdf/2510.23587
β€’ Github: https://github.com/HKUSTDial/awesome-data-agents

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Code Aesthetics with Agentic Reward Feedback

πŸ”Ή Publication Date: Published on Oct 27

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.23272
β€’ PDF: https://arxiv.org/pdf/2510.23272
β€’ Project Page: https://bangx7.github.io/code-aesthetics/

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Memory-based Language Models: An Efficient, Explainable, and Eco-friendly Approach to Large Language Modeling

πŸ”Ή Publication Date: Published on Oct 25

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.22317
β€’ PDF: https://arxiv.org/pdf/2510.22317
β€’ Github: https://github.com/antalvdb/olifant

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMS

πŸ”Ή Publication Date: Published on Oct 26

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.22603
β€’ PDF: https://arxiv.org/pdf/2510.22603
β€’ Github: https://github.com/umbertocappellazzo/Llama-AVSR

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
❀1
πŸ€–πŸ§  Free for 1 Year: ChatGPT Go’s Big Move in India

πŸ—“οΈ 28 Oct 2025
πŸ“š AI News & Trends

On 28 October 2025, OpenAI announced that its mid-tier subscription plan, ChatGPT Go, will be available free for one full year in India starting from 4 November. (www.ndtv.com) What is ChatGPT Go? What’s the deal? Why this matters ? Things to check / caveats What should users do? Broader implications This move by OpenAI indicates ...

#ChatGPTGo #OpenAI #India #FreeAccess #ArtificialIntelligence #TechNews
πŸ”Ή Title: The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation

πŸ”Ή Publication Date: Published on Oct 27

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.23393
β€’ PDF: https://arxiv.org/pdf/2510.23393

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: EchoDistill: Bidirectional Concept Distillation for One-Step Diffusion Personalization

πŸ”Ή Publication Date: Published on Oct 23

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.20512
β€’ PDF: https://arxiv.org/pdf/2510.20512

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”Ή Title: DiffusionLane: Diffusion Model for Lane Detection

πŸ”Ή Publication Date: Published on Oct 25

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.22236
β€’ PDF: https://arxiv.org/pdf/2510.22236

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ‘1
πŸ”Ή Title: Scaling Laws for Deepfake Detection

πŸ”Ή Publication Date: Published on Oct 18

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.16320
β€’ PDF: https://arxiv.org/pdf/2510.16320

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ‘1
πŸ”Ή Title: SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction

πŸ”Ή Publication Date: Published on Oct 9

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.07723
β€’ PDF: https://arxiv.org/pdf/2510.07723

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ”₯1
πŸ”Ή Title: Once Upon an Input: Reasoning via Per-Instance Program Synthesis

πŸ”Ή Publication Date: Published on Oct 26

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.22849
β€’ PDF: https://arxiv.org/pdf/2510.22849
β€’ Github: https://github.com/adaminsky/pips

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
❀2
πŸ”Ή Title: Open Multimodal Retrieval-Augmented Factual Image Generation

πŸ”Ή Publication Date: Published on Oct 26

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.22521
β€’ PDF: https://arxiv.org/pdf/2510.22521
β€’ Project Page: https://tyangjn.github.io/orig.github.io/
β€’ Github: https://github.com/TyangJN/ORIG

πŸ”Ή Datasets citing this paper:
β€’ https://huggingface.co/datasets/TyangJN/FIG

πŸ”Ή Spaces citing this paper:
No spaces found
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
πŸ‘1
πŸ”Ή Title: FlowOpt: Fast Optimization Through Whole Flow Processes for Training-Free Editing

πŸ”Ή Publication Date: Published on Oct 24

πŸ”Ή Paper Links:
β€’ arXiv Page: https://arxiv.org/abs/2510.22010
β€’ PDF: https://arxiv.org/pdf/2510.22010
β€’ Project Page: https://orronai.github.io/FlowOpt/
β€’ Github: https://github.com/orronai/FlowOpt

πŸ”Ή Datasets citing this paper:
No datasets found

πŸ”Ή Spaces citing this paper:
β€’ https://huggingface.co/spaces/orronai/FlowOpt
==================================

For more data science resources:
βœ“ https://t.me/DataScienceT
❀2