Yury Panikov

panikov's activity

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

upvoted 20 papers 6 days ago

GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI Grounding

Paper • 2511.00810 • Published 9 days ago • 3

Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement

Paper • 2511.01706 • Published 8 days ago • 2

Vote-in-Context: Turning VLMs into Zero-Shot Rank Fusers

Paper • 2511.01617 • Published 8 days ago • 2

UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings

Paper • 2511.00405 • Published 10 days ago • 5

Data-Efficient RLVR via Off-Policy Influence Guidance

Paper • 2510.26491 • Published 12 days ago • 8

MotionStream: Real-Time Video Generation with Interactive Motion Controls

Paper • 2511.01266 • Published 8 days ago • 24

EBT-Policy: Energy Unlocks Emergent Physical Reasoning Capabilities

Paper • 2510.27545 • Published 11 days ago • 47

How Far Are Surgeons from Surgical World Models? A Pilot Study on Zero-shot Surgical Video Generation with Expert Assessment

Paper • 2511.01775 • Published 8 days ago • 6

Towards Robust Mathematical Reasoning

Paper • 2511.01846 • Published 7 days ago • 7

Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models

Paper • 2511.01618 • Published 8 days ago • 9

left|,circlearrowright,text{BUS},right|: A Large and Diverse Multimodal Benchmark for evaluating the ability of Vision-Language Models to understand Rebus Puzzles

Paper • 2511.01340 • Published 8 days ago • 12

Do Vision-Language Models Measure Up? Benchmarking Visual Measurement Reading with MeasureBench

Paper • 2510.26865 • Published 12 days ago • 11

Trove: A Flexible Toolkit for Dense Retrieval

Paper • 2511.01857 • Published 7 days ago • 10

NaviTrace: Evaluating Embodied Navigation of Vision-Language Models

Paper • 2510.26909 • Published 11 days ago • 13

LongCat-Flash-Omni Technical Report

Paper • 2511.00279 • Published 10 days ago • 21

TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning

Paper • 2511.01833 • Published 7 days ago • 15

OpenSIR: Open-Ended Self-Improving Reasoner

Paper • 2511.00602 • Published 10 days ago • 20

MR-Align: Meta-Reasoning Informed Factuality Alignment for Large Reasoning Models

Paper • 2510.24794 • Published 15 days ago • 31

Towards Universal Video Retrieval: Generalizing Video Embedding via Synthesized Multimodal Pyramid Curriculum

Paper • 2510.27571 • Published 11 days ago • 16

ToolScope: An Agentic Framework for Vision-Guided and Long-Horizon Tool Use

Paper • 2510.27363 • Published 11 days ago • 22