new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

byAK and the research community

Sep 16

Submitted by

taesiri

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

·
19 authors

Submitted by

xhyandwyy

UI-S1: Advancing GUI Automation via Semi-online Reinforcement Learning

·
11 authors

Submitted by

taesiri

InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts

·
12 authors

Submitted by

taesiri

LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence

·
7 authors

Submitted by

Iman998

SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation

·
3 authors

Submitted by

ylu610

Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting

·
9 authors

Submitted by

ottogin

Locality in Image Diffusion Models Emerges from Data Statistics

·
4 authors

Submitted by

lyan62

Lost in Embeddings: Information Loss in Vision-Language Models

·
6 authors

2

Submitted by

kaiyangzhou

Measuring Epistemic Humility in Multimodal Large Language Models

·
4 authors

Submitted by

taesiri

Nav-R1: Reasoning and Navigation in Embodied Scenes

·
4 authors

Submitted by

Macro

Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Models

·
6 authors

Submitted by

gauravfs-14

CognitiveSky: Scalable Sentiment and Narrative Analysis for Decentralized Social Media

·
3 authors

Submitted by

taesiri

PersonaX: Multimodal Datasets with LLM-Inferred Behavior Traits

·
10 authors

Submitted by

Eureka-Leo

Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding

·
15 authors

Submitted by

UVSKKR

EthicsMH: A Pilot Benchmark for Ethical Reasoning in Mental Health AI

·
1 authors

2

Submitted by

AnirbanSaha

ClaimIQ at CheckThat! 2025: Comparing Prompted and Fine-Tuned Language Models for Verifying Numerical Claims

·
4 authors

Submitted by

amanchadha

FuseCodec: Semantic-Contextual Fusion and Supervision for Neural Codecs

·
9 authors

Submitted by

yixuantt

GAPrune: Gradient-Alignment Pruning for Domain-Aware Embeddings

·
2 authors

Submitted by

mayankagarwal

ToolRM: Outcome Reward Models for Tool-Calling Large Language Models

·
7 authors

Submitted by

Cloudriver

LongEmotion: Measuring Emotional Intelligence of Large Language Models in Long-Context Interaction

·
14 authors

2