Voozh

AI & ML interests

Natural Language Processing, Machine Learning, and Computer Vision

Recent Activity

👁 Image

amoriodi authored a paper 6 days ago

FlexInfer: Breaking Memory Constraint via Flexible and Efficient Offloading for On-Device LLM Inference

👁 Image

amoriodi authored a paper 6 days ago

Learning Quantised Structure-Preserving Motion Representations for Dance Fingerprinting

👁 Image

amoriodi authored a paper 6 days ago

Exposing Hidden Interfaces: LLM-Guided Type Inference for Reverse Engineering macOS Private Frameworks

View all activity

Papers

👁 Image

CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization

👁 Image

SafeDiffusion-R1: Online Reward Steering for Safe Diffusion Post-Training

View all Papers

👁 Image

Submitted by

👁 Image

Ahmed Heakl

CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

11 1

👁 Image

Submitted by

👁 Image

Komal Kumar

SafeDiffusion-R1: Online Reward Steering for Safe Diffusion Post-Training

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

5 1

👁 Image

Submitted by

👁 Image

Do Thanh Tung

Efficient Image Synthesis with Sphere Latent Encoder

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

👁 Image

Submitted by

👁 Image

Ahmed Heakl

DocAtlas: Multilingual Document Understanding Across 80+ Languages

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

0 2

👁 Image

Submitted by

👁 Image

Xingyu Qu

Can Muon Fine-tune Adam-Pretrained Models?

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

👁 Image

Submitted by

👁 Image

Naoto Iwase

Reliable Chain-of-Thought via Prefix Consistency

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

1 3

👁 Image

Submitted by

👁 Image

Kareem Elozeiri

Instruction-Guided Poetry Generation in Arabic and Its Dialects

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

1 2

👁 Image

Submitted by

👁 Image

Akash Ghosh

When Background Matters: Breaking Medical Vision Language Models by Transferable Attack

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

2 2

👁 Image

Submitted by

👁 Image

Duy Le

Counting to Four is still a Chore for VLMs

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

0 2

👁 Image

Submitted by

👁 Image

Komal Kumar

Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

95 3

👁 Image

Submitted by

👁 Image

Patrick Amadeus Irawan

LinguDistill: Recovering Linguistic Ability in Vision- Language Models via Selective Cross-Modal Distillation

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

👁 Image

Submitted by

👁 Image

Akash Ghosh

CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcare

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

21 2

👁 Image

Submitted by

👁 Image

Zhiqiang Shen

From Masks to Pixels and Meaning: A New Taxonomy, Benchmark, and Metrics for VLM Image Tampering

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

14 2

👁 Image

Submitted by

👁 Image

Tingxu Han

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

54 2

👁 Image

World2Act: Latent Action Post-Training via Skill-Compositional World Models

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

Submitted by

👁 Image

Sahal Shaji

MediX-R1: Open Ended Medical Reinforcement Learning

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

63 2

👁 Image

Submitted by

👁 Image

Ahmed Heakl

Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

150 3

👁 Image

Submitted by

👁 Image

Aidar Myrzakhan

Sink-Aware Pruning for Diffusion Language Models

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

13 2

👁 Image

Submitted by

👁 Image

Sahal Shaji

A Benchmark and Agentic Framework for Omni-Modal Reasoning and Tool Use in Long Videos

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

21 2

👁 Image

Submitted by

👁 Image

SARIM HASHMI

Robust and Calibrated Detection of Authentic Multimedia Content

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

👁 Image

Submitted by

👁 Image

Mukul Ranjan

Attention Is All You Need for KV Cache in Diffusion LLMs

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

👁 Image

Submitted by

👁 Image

Chenxi Wang

Do LLMs "Feel"? Emotion Circuits Discovery and Control

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

👁 Image

Submitted by

👁 Image

Tingting Liao

Character Mixing for Video Generation

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

83 2

👁 Image

How Good are Foundation Models in Step-by-Step Embodied Reasoning?

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

👁 Image

The Good, the Bad and the Constructive: Automatically Measuring Peer Review's Utility for Authors

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

👁 Image

Submitted by

👁 Image

Ahmed Heakl

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

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

5 2

Submitted by

👁 Image

Ahmed Heakl

VideoMolmo: Spatio-Temporal Grounding Meets Pointing

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

56 6

👁 Image

Submitted by

👁 Image

Ahmed Heakl

SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

16 2

👁 Image

Submitted by

👁 Image

Ahmed Heakl

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

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

34 5

👁 Image

Submitted by

👁 Image

Ahmed Heakl

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

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

71 2

👁 Image

Submitted by

👁 Image

Ahmed Heakl

AIN: The Arabic INclusive Large Multimodal Model

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

54 2

👁 Image

Submitted by

👁 Image

Ahmed Heakl

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

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

308 5

👁 Image

Submitted by

👁 Image

Ahmed Heakl

From CISC to RISC: language-model guided assembly transpilation

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

👁 Image

Submitted by

👁 Image

Shehan Munasinghe

VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

104 3

👁 Image

Submitted by

👁 Image

Ahmed Heakl

CAMEL-Bench: A Comprehensive Arabic LMM Benchmark

👁 MBZUAI
Mohamed Bin Zayed University of Artificial Intelligence

38 2

URL: https://huggingface.co/MBZUAI/papers

⇱ MBZUAI (Mohamed Bin Zayed University of Artificial Intelligence)

AI & ML interests

Recent Activity

Papers

CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization

SafeDiffusion-R1: Online Reward Steering for Safe Diffusion Post-Training

Efficient Image Synthesis with Sphere Latent Encoder

DocAtlas: Multilingual Document Understanding Across 80+ Languages

Can Muon Fine-tune Adam-Pretrained Models?

Reliable Chain-of-Thought via Prefix Consistency

Instruction-Guided Poetry Generation in Arabic and Its Dialects

When Background Matters: Breaking Medical Vision Language Models by Transferable Attack

Counting to Four is still a Chore for VLMs

Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework

LinguDistill: Recovering Linguistic Ability in Vision- Language Models via Selective Cross-Modal Distillation

CarePilot: A Multi-Agent Framework for Long-Horizon Computer Task Automation in Healthcare

From Masks to Pixels and Meaning: A New Taxonomy, Benchmark, and Metrics for VLM Image Tampering

SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?

World2Act: Latent Action Post-Training via Skill-Compositional World Models

MediX-R1: Open Ended Medical Reinforcement Learning

Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device

Sink-Aware Pruning for Diffusion Language Models

A Benchmark and Agentic Framework for Omni-Modal Reasoning and Tool Use in Long Videos

Robust and Calibrated Detection of Authentic Multimedia Content

Attention Is All You Need for KV Cache in Diffusion LLMs

Do LLMs "Feel"? Emotion Circuits Discovery and Control

Character Mixing for Video Generation

How Good are Foundation Models in Step-by-Step Embodied Reasoning?

The Good, the Bad and the Constructive: Automatically Measuring Peer Review's Utility for Authors

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

VideoMolmo: Spatio-Temporal Grounding Meets Pointing

SVRPBench: A Realistic Benchmark for Stochastic Vehicle Routing Problem

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

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

AIN: The Arabic INclusive Large Multimodal Model

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

From CISC to RISC: language-model guided assembly transpilation

VideoGLaMM: A Large Multimodal Model for Pixel-Level Visual Grounding in Videos

CAMEL-Bench: A Comprehensive Arabic LMM Benchmark