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

Apr 1

Submitted by

zhen-nan

TextCrafter: Accurately Rendering Multiple Texts in Complex Visual Scenes

·
8 authors

3

Submitted by

lim142857

MoCha: Towards Movie-Grade Talking Character Synthesis

·
13 authors

5

Submitted by

akhaliq

Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

·
6 authors

Submitted by

DonJoey

What, How, Where, and How Well? A Survey on Test-Time Scaling in Large Language Models

·
10 authors

2

Submitted by

yueliu1999

Efficient Inference for Large Reasoning Models: A Survey

·
9 authors

3

Submitted by

Wizardcoast

Unicorn: Text-Only Data Synthesis for Vision Language Model Training

·
10 authors

Submitted by

vanilla1116

RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy

·
7 authors

Submitted by

lianganimation

TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization

·
8 authors

2

Submitted by

Okrin

SketchVideo: Sketch-based Video Generation and Editing

·
7 authors

3

Submitted by

tongwu2020

Effectively Controlling Reasoning Models through Thinking Intervention

·
4 authors

3

Submitted by

Borchmann

Query and Conquer: Execution-Guided SQL Generation

·
2 authors

2

Submitted by

akhaliq

Expanding RL with Verifiable Rewards Across Diverse Domains

·
8 authors

Submitted by

ZhiyuanthePony

Progressive Rendering Distillation: Adapting Stable Diffusion for Instant Text-to-Mesh Generation without 3D Data

·
6 authors

2

Submitted by

JimmyMa99

TeleAntiFraud-28k: A Audio-Text Slow-Thinking Dataset for Telecom Fraud Detection

·
10 authors

2

Submitted by

jianguozhang

ActionStudio: A Lightweight Framework for Data and Training of Large Action Models

·
16 authors

Submitted by

abcorrea

Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code

·
3 authors

1

Submitted by

rover-xingyu

Easi3R: Estimating Disentangled Motion from DUSt3R Without Training

·
5 authors

2

Submitted by

77Hui

UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation

·
10 authors

2

Submitted by

Lp256

MeshCraft: Exploring Efficient and Controllable Mesh Generation with Flow-based DiTs

·
8 authors

Submitted by

lastdefiance20

KOFFVQA: An Objectively Evaluated Free-form VQA Benchmark for Large Vision-Language Models in the Korean Language

·
2 authors

2

Submitted by

ZhenyuLiang

Bridging Evolutionary Multiobjective Optimization and GPU Acceleration via Tensorization

·
5 authors

3

Submitted by

xw27

Entropy-Based Adaptive Weighting for Self-Training

·
4 authors

Submitted by

akhaliq

DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness

·
4 authors

Submitted by

KumaPower

AvatarArtist: Open-Domain 4D Avatarization

·
9 authors

2

Submitted by

zhuomingliu

PAVE: Patching and Adapting Video Large Language Models

·
5 authors

2

Submitted by

mwbini

Decoupling Angles and Strength in Low-rank Adaptation

·
3 authors

2

Submitted by

sindhuhegde

Understanding Co-speech Gestures in-the-wild

·
4 authors

2