Ahmed Heakl PRO

ahmedheakl's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 20 days ago

Robust and Calibrated Detection of Authentic Multimedia Content

Paper • 2512.15182 • Published 21 days ago • 15

upvoted a paper about 2 months ago

PAN: A World Model for General, Interactable, and Long-Horizon World Simulation

Paper • 2511.09057 • Published Nov 12, 2025 • 76

upvoted 2 papers 3 months ago

Attention Is All You Need for KV Cache in Diffusion LLMs

Paper • 2510.14973 • Published Oct 16, 2025 • 40

Dr.LLM: Dynamic Layer Routing in LLMs

Paper • 2510.12773 • Published Oct 14, 2025 • 31

upvoted 2 papers 7 months ago

VideoMolmo: Spatio-Temporal Grounding Meets Pointing

Paper • 2506.05336 • Published Jun 5, 2025 • 9

Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guarantees

Paper • 2506.14606 • Published Jun 17, 2025 • 11

upvoted a collection 7 months ago

CASS

Collection

CUDA to AMD Transpilation with Data, Models, and Benchmarks • 10 items • Updated Jun 4, 2025 • 1

upvoted 3 papers 7 months ago

Time Blindness: Why Video-Language Models Can't See What Humans Can?

Paper • 2505.24867 • Published May 30, 2025 • 80

SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem

Paper • 2505.21887 • Published May 28, 2025 • 14

CASS: Nvidia to AMD Transpilation with Data, Models, and Benchmark

Paper • 2505.16968 • Published May 22, 2025 • 40

upvoted a collection 8 months ago

CASS

Collection

Large-scale dataset and model suite for cross-architecture GPU code transpilation between CUDA and HIP at both source and assembly levels • 2 items • Updated May 15, 2025 • 5

upvoted a paper 10 months ago

SALT: Singular Value Adaptation with Low-Rank Transformation

Paper • 2503.16055 • Published Mar 20, 2025 • 8

upvoted an article 10 months ago

view article

Article

Arabic LLM Models

• 

Mar 4, 2025

•

42

upvoted a collection 11 months ago

KITAB-Bench

Collection

A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding • 24 items • Updated Feb 24, 2025 • 16

upvoted a paper 11 months ago

KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understanding

Paper • 2502.14949 • Published Feb 20, 2025 • 9

upvoted an article 11 months ago

view article

Article

Fish Speech V1 - New Multilingual Open Source TTS Model

• 

May 3, 2024

•

19

upvoted a paper 11 months ago

AIN: The Arabic INclusive Large Multimodal Model

Paper • 2502.00094 • Published Jan 31, 2025 • 18

upvoted a paper 12 months ago

LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs

Paper • 2501.06186 • Published Jan 10, 2025 • 65

upvoted 2 papers about 1 year ago

BiMediX2: Bio-Medical EXpert LMM for Diverse Medical Modalities

Paper • 2412.07769 • Published Dec 10, 2024 • 30

From CISC to RISC: language-model guided assembly transpilation

Paper • 2411.16341 • Published Nov 25, 2024 • 14