Mohamed Elhoseiny

Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-in

Neural Catalog: Scaling Species Recognition with Catalog of Life–Augmented Generation

Look&Learn: Where to Look? Bridging Perception and Grounding Gap in Vision-Language Models

$1+1<1$? Breaking the Standalone Barrier in Federated Fine-Tuning of Multimodal Large Language Models under Non-IID Data

AutoDavis: Automatic and Dynamic Evaluation Protocol of Large Vision-Language Models on Visual Question-Answering

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

EvoCurr: Self-evolving Curriculum with Behavior Code Generation for Complex Decision-making

Cross-Reflect: Empowering Multi-Modal Agents with Joint Reasoning Across Trajectories

FishNet++: Analyzing the capabilities of Multimodal Large Language Models in marine biology.

AVSU-Bench and VSpeech-R1: A Dataset and MLLM for Audio-Visual Speech Understanding

ReefNet: A Large-Scale, Taxonomically Enriched Dataset and Benchmark for Hard Coral Classification

Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding

Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models

MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schrödinger Bridge

InfiniBench: A Comprehensive Benchmark for Large Multimodal Models in Very Long Video Understanding

Query-based Knowledge Transfer for Heterogeneous Learning Environments

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

ReferPix2Pix: Guiding Multi-Modal LLMs for Image Editing with Referential Pixel Grounding

StoryGPT-V: Large Language Models as Consistent Story Visualizers

HuMouS: Human Motion Synthesis with Fine-Grained Control using Latent Space Manipulation of Cycle-Consistent Diffusion Models

AutoBench-V: Can Large Vision-Language Models Benchmark Themselves?

iMotion-LLM: Motion Prediction Instruction Tuning