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

Jun 24

Submitted by

chongjie

Light of Normals: Unified Feature Representation for Universal Photometric Stereo

·
14 authors

Submitted by

JUNJIE99

OmniGen2: Exploration to Advanced Multimodal Generation

·
22 authors

Submitted by

mozhu

LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning

·
5 authors

Submitted by

michaal94

ViDAR: Video Diffusion-Aware 4D Reconstruction From Monocular Inputs

·
6 authors

1

Submitted by

Lingaaaaaaa

ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs

·
7 authors

Submitted by

ZhuoweiChen

Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset

·
11 authors

Submitted by

Yirany

RLPR: Extrapolating RLVR to General Domains without Verifiers

·
12 authors

Submitted by

Wangchunshu

OAgents: An Empirical Study of Building Effective Agents

·
24 authors

Submitted by

csuhan

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

·
9 authors

Submitted by

liguang0115

VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory

·
4 authors

Submitted by

sgidaris

DIP: Unsupervised Dense In-Context Post-training of Visual Representations

·
5 authors

Submitted by

vyokky

LettinGo: Explore User Profile Generation for Recommendation System

·
12 authors

Submitted by

ashmrz

4Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation

·
12 authors

Submitted by

wenqsun

From Virtual Games to Real-World Play

·
8 authors

1

Submitted by

cliang1453

SlimMoE: Structured Compression of Large MoE Models via Expert Slimming and Distillation

·
7 authors

Submitted by

manglu3935

Enhancing Step-by-Step and Verifiable Medical Reasoning in MLLMs

·
9 authors

Submitted by

natnitaract

FinCoT: Grounding Chain-of-Thought in Expert Financial Reasoning

·
6 authors

Submitted by

LogicTrainer

TC-Light: Temporally Consistent Relighting for Dynamic Long Videos

·
9 authors

Submitted by

kittttttt

ReDit: Reward Dithering for Improved LLM Policy Optimization

·
6 authors

Submitted by

kamahori

ConsumerBench: Benchmarking Generative AI Applications on End-User Devices

·
6 authors

Submitted by

pragsri8

Robust Reward Modeling via Causal Rubrics

·
12 authors

2

Submitted by

vanshs1

Steering Conceptual Bias via Transformer Latent-Subspace Activation

·
2 authors

1

Submitted by

dylanebert

3D Arena: An Open Platform for Generative 3D Evaluation

·
1 authors

1

Submitted by

Jiakui

Auto-Regressively Generating Multi-View Consistent Images

·
6 authors

Submitted by

seonglae

FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies

·
6 authors

Submitted by

senfu

CommVQ: Commutative Vector Quantization for KV Cache Compression

·
11 authors

1

Submitted by

chromeNLP

How Alignment Shrinks the Generative Horizon

·
2 authors

Submitted by

Neo111x

I Know Which LLM Wrote Your Code Last Summer: LLM generated Code Stylometry for Authorship Attribution

·
9 authors

Submitted by

shuoxing

Demystifying the Visual Quality Paradox in Multimodal Large Language Models

·
8 authors

Submitted by

Shoubin

4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time

·
13 authors

Submitted by

BoKelvin

GEMeX-ThinkVG: Towards Thinking with Visual Grounding in Medical VQA via Reinforcement Learning

·
6 authors

1

Submitted by

akanatas

CultureMERT: Continual Pre-Training for Cross-Cultural Music Representation Learning

·
3 authors

1

Submitted by

xunguangwang

SoK: Evaluating Jailbreak Guardrails for Large Language Models

·
6 authors

2

Submitted by

tahirakazimi77

Audit & Repair: An Agentic Framework for Consistent Story Visualization in Text-to-Image Diffusion Models

·
3 authors

1

Submitted by

Yeongtak

RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models

·
7 authors

Submitted by

ffurfaro

TPTT: Transforming Pretrained Transformer into Titans

·
1 authors

Submitted by

rajandasgupta

A deep learning and machine learning approach to predict neonatal death in the context of São Paulo

·
9 authors

2

Submitted by

kevin1020

Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent Systems

·
6 authors

Submitted by

xwjzds

Quantifying Fairness in LLMs Beyond Tokens: A Semantic and Statistical Perspective

·
7 authors