new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

by AK and the research community

Dec 4

Submitted by

BestWishYsh

VideoGen-of-Thought: A Collaborative Framework for Multi-Shot Video Generation

·
11 authors

Submitted by

Lin1557

Critical Tokens Matter: Token-Level Contrastive Estimation Enhence LLM's Reasoning Capability

·
9 authors

Submitted by

r0nn13

MALT: Improving Reasoning with Multi-Agent LLM Training

·
9 authors

Submitted by

lievan

Free Process Rewards without Process Labels

·
9 authors

Submitted by

YiwuZhong

AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning

·
4 authors

Submitted by

KaituoFeng

AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information?

·
11 authors

Submitted by

wanderkid

OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation

·
9 authors

Submitted by

PereLluis13

Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-OASIS

·
6 authors

Submitted by

irwinherrmann

Motion Prompting: Controlling Video Generation with Motion Trajectories

·
14 authors

Submitted by

Jethro37

OmniCreator: Self-Supervised Unified Generation with Universal Editing

·
4 authors

Submitted by

Hoyard

LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences

·
9 authors

Submitted by

yifAI

Scaling Image Tokenizers with Grouped Spherical Quantization

·
7 authors

Submitted by

bhheo

MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation

·
6 authors

Submitted by

Haihao

A dynamic parallel method for performance optimization on hybrid CPUs

·
3 authors

Submitted by

patricebechard

Generating a Low-code Complete Workflow via Task Decomposition and RAG

·
2 authors

Submitted by

dpaul06

VideoLights: Feature Refinement and Cross-Task Alignment Transformer for Joint Video Highlight Detection and Moment Retrieval

·
4 authors