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 26

Submitted by

taesiri

InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency

·
61 authors

Submitted by

taesiri

Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation

·
9 authors

Submitted by

yosepyossi

MV-RAG: Retrieval Augmented Multiview Diffusion

·
3 authors

Submitted by

Kaiyue

T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation

·
5 authors

Submitted by

Ironieser

MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs

·
6 authors

Submitted by

BAOLONGZHANSHEN

Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning

·
13 authors

2

Submitted by

mbur

Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling

·
12 authors

Submitted by

sumuks

Hermes 4 Technical Report

·
9 authors

Submitted by

Wyattz23

PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs

·
5 authors

Submitted by

Muennighoff

UQ: Assessing Language Models on Unsolved Questions

·
14 authors

Submitted by

omidgh

MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment

·
11 authors

2

Submitted by

taesiri

ST-Raptor: LLM-Powered Semi-Structured Table Question Answering

·
9 authors

Submitted by

zhongwenxu

Understanding Tool-Integrated Reasoning

·
2 authors

Submitted by

ControlNet

Explain Before You Answer: A Survey on Compositional Visual Reasoning

·
13 authors

Submitted by

Hecheng0625

TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling

·
6 authors

Submitted by

taesiri

SpotEdit: Evaluating Visually-Guided Image Editing Methods

·
4 authors

Submitted by

taesiri

Neither Valid nor Reliable? Investigating the Use of LLMs as Judges

·
4 authors

Submitted by

stefan-it

German4All - A Dataset and Model for Readability-Controlled Paraphrasing in German

·
6 authors

Submitted by

mbur

Limitations of Normalization in Attention Mechanism

·
4 authors

5

Submitted by

RuijieZhu

MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting

·
8 authors

Submitted by

tristan-deep

Semantic Diffusion Posterior Sampling for Cardiac Ultrasound Dehazing

·
3 authors

Submitted by

stefanos50

REGEN: Real-Time Photorealism Enhancement in Games via a Dual-Stage Generative Network Framework

·
2 authors

Submitted by

dipta007

If We May De-Presuppose: Robustly Verifying Claims through Presupposition-Free Question Decomposition

·
2 authors