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

Aug 19

Submitted by

runninglsy

Ovis2.5 Technical Report

·
42 authors

Submitted by

lxucs

ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

·
8 authors

Submitted by

tqliu

4DNeX: Feed-Forward 4D Generative Modeling Made Easy

·
9 authors

Submitted by

weigao266

Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

·
15 authors

Submitted by

yikaiwang

Next Visual Granularity Generation

·
6 authors

Submitted by

taesiri

S^2-Guidance: Stochastic Self Guidance for Training-Free Enhancement of Diffusion Models

·
9 authors

Submitted by

myyycroft

When Punctuation Matters: A Large-Scale Comparison of Prompt Robustness Methods for LLMs

·
6 authors

Submitted by

caizhongang

Has GPT-5 Achieved Spatial Intelligence? An Empirical Study

·
22 authors

2

Submitted by

taesiri

Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model

·
19 authors

Submitted by

petranokhin

HeroBench: A Benchmark for Long-Horizon Planning and Structured Reasoning in Virtual Worlds

·
6 authors

Submitted by

klemenk

Representing Speech Through Autoregressive Prediction of Cochlear Tokens

·
4 authors

2

Submitted by

taesiri

Lumen: Consistent Video Relighting and Harmonious Background Replacement with Video Generative Models

·
9 authors

Submitted by

grason-lu

Reinforcement Learning with Rubric Anchors

·
21 authors

2

Submitted by

rusrakhimov

G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration

·
5 authors

2

Submitted by

walsvid

Precise Action-to-Video Generation Through Visual Action Prompts

·
8 authors

2

Submitted by

xuhuizhan5

Inverse-LLaVA: Eliminating Alignment Pre-training Through Text-to-Vision Mapping

·
2 authors

Submitted by

jaeunglee

Unlearning Comparator: A Visual Analytics System for Comparative Evaluation of Machine Unlearning Methods

·
5 authors

Submitted by

YouchengHuang

Beyond Solving Math Quiz: Evaluating the Ability of Large Reasoning Models to Ask for Information

·
6 authors

3

Submitted by

j-min

RotBench: Evaluating Multimodal Large Language Models on Identifying Image Rotation

·
4 authors